© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11315
    Prev
    Next
    INDEX
    Explanations

    words related to engagement in some pursuit.

    oai_token-act-pair · gemini-2.0-flash

    non-English words or diverse terms

    np_token-act-pair-logits · gpt-4o-mini

    activity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    RectangleBorder
    -0.69
     Roskov
    -0.67
    andaag
    -0.64
    󠁮
    -0.60
    CodedInputStream
    -0.59
    adpleegd
    -0.58
    initWithFrame
    -0.56
    ReusableCell
    -0.55
    -------------</
    -0.54
     onData
    -0.54
    POSITIVE LOGITS
    gantian
    0.50
    ContentAsync
    0.49
     שוליים
    0.45
     تضيفلها
    0.45
     fingernails
    0.44
     joyería
    0.43
    Dislikes
    0.43
     képes
    0.42
     dignité
    0.42
     Fink
    0.42
    Activations Density 5.860%

    No Known Activations