© 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. 6327
    Prev
    Next
    INDEX
    Explanations

    code from an installation script

    oai_token-act-pair · gemini-2.0-flash

    Code and file paths

    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
    "{\
    -0.71
    \",\
    -0.70
    )•
    -0.69
    ViewFeatures
    -0.69
    DIPSETTING
    -0.66
    :✨
    -0.65
     thiệu
    -0.63
    Билгалдахарш
    -0.63
    enumii
    -0.61
    AsyncResult
    -0.61
    POSITIVE LOGITS
    ');?>
    0.54
    '}>
    0.52
    ')}}">
    0.49
    </code>
    0.46
    0.45
     للمعارف
    0.45
    共に
    0.45
    '])){

    0.44
    </b>
    0.43
     ô
    0.43
    Activations Density 1.288%
    No Known Activations