© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13978
    Prev
    Next
    INDEX
    Explanations

    legal citations

    oai_token-act-pair · gemini-2.0-flash

    asterisk

    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
    Personensuche
    -0.76
    
    -0.65
    <?
    -0.61
    Попис
    -0.57
    expandindo
    -0.54
     actualité
    -0.54
    دانشنامهٔ
    -0.53
     ujednoznacz
    -0.48
    !("{}",
    -0.47
     daß
    -0.46
    POSITIVE LOGITS
    providedIn
    0.67
    MetaObject
    0.64
     '>=
    0.61
    nocześnie
    0.59
    eme
    0.57
    GraphicsUnit
    0.55
    WithIdentifier
    0.55
    DECREF
    0.55
    XDECREF
    0.54
    XtraBars
    0.54
    Activations Density 3.154%

    No Known Activations