© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7623
    Prev
    Next
    INDEX
    Explanations

    words and abbreviations related to scientific and medical imaging and analysis techniques.

    oai_token-act-pair · gemini-2.0-flash

    Scientific/Technical Reports

    np_max-act-logits · gemini-2.0-flash

    acronyms Method used: 1 — because the max-activating tokens are all uppercase acronyms; acronyms

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.74
     invokingState
    -0.67
    تقاوى
    -0.67
    SequentialGroup
    -0.63
     Geraadpleegd
    -0.62
     ejus
    -0.60
     eorum
    -0.57
    reactstrap
    -0.56
    LookAnd
    -0.56
    الدراسه
    -0.55
    POSITIVE LOGITS
    worm
    0.54
    erver
    0.50
    TRAP
    0.46
    mender
    0.43
    monic
    0.43
    runner
    0.43
    miner
    0.42
    mentation
    0.40
    trap
    0.39
    STER
    0.39
    Activations Density 33.686%

    No Known Activations