© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11714
    Prev
    Next
    INDEX
    Explanations

    mentions of coding or medical practice

    oai_token-act-pair · gemini-2.0-flash

    Rules, guidelines, best practices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     AGENCY
    -0.47
     souff
    -0.46
     sī
    -0.45
     Agency
    -0.44
    halle
    -0.43
    лец
    -0.42
    Agency
    -0.41
    fuss
    -0.40
    во
    -0.40
    ộc
    -0.40
    POSITIVE LOGITS
    AndEndTag
    1.05
    DoubleQuotes
    0.94
    Personendaten
    0.93
    providedIn
    0.93
     فريبيس
    0.90
     виправивши
    0.89
    AsUp
    0.86
     للاسماء
    0.85
    tvguidetime
    0.85
     Италијани
    0.84
    Activations Density 1.528%

    No Known Activations