© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6933
    Prev
    Next
    INDEX
    Explanations

    dates

    oai_token-act-pair · gemini-2.0-flash

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    bootstrapcdn
    -0.57
    cassert
    -0.49
    GNUC
    -0.47
     '\\;'
    -0.46
     kasarigan
    -0.44
    asInstanceOf
    -0.44
     élu
    -0.43
     CURIAM
    -0.43
    ci
    -0.43
    сування
    -0.42
    POSITIVE LOGITS
     EnglishChoose
    0.64
    setVerticalGroup
    0.58
     (!__
    0.57
    rdom
    0.57
     Zeno
    0.56
    WithMany
    0.54
     ¦
    0.53
    ibatis
    0.53
     beginnetje
    0.53
     Channing
    0.52
    Activations Density 0.519%

    No Known Activations