© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5137
    Prev
    Next
    INDEX
    Explanations

    programming code and physics terms

    oai_token-act-pair · gemini-2.0-flash

    magne

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ed
    -1.37
    ever
    -1.20
    ians
    -1.13
    ian
    -1.12
    earch
    -1.09
    ities
    -1.09
    ew
    -1.05
     propOrder
    -1.05
    ised
    -1.02
    ive
    -1.00
    POSITIVE LOGITS
    son
    0.37
    ert
    0.36
    led
    0.36
    ser
    0.35
    ת
    0.35
    ori
    0.34
    로
    0.34
     disturbing
    0.33
    ل
    0.33
    ted
    0.33
    Activations Density 7.950%

    No Known Activations