© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15975
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to dental procedures

    oai_token-act-pair · gemini-2.0-flash

    compromise

    np_max-act-logits · gemini-2.0-flash
    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
     Мексичка
    -0.76
    $_['
    -0.74
    writeFieldEnd
    -0.70
    ########.
    -0.68
    UnknownFields
    -0.63
    ecma
    -0.61
    ьаж
    -0.60
     StatefulWidget
    -0.59
    stdc
    -0.57
    WebElementEntity
    -0.57
    POSITIVE LOGITS
    mely
    0.49
    帖最后由
    0.45
     Delgado
    0.43
     tys
    0.43
    folia
    0.42
     toho
    0.42
    DebuggerStep
    0.42
     Asunción
    0.42
    awtextra
    0.41
    owal
    0.41
    Activations Density 5.657%

    No Known Activations