© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8582
    Prev
    Next
    INDEX
    Explanations

    a wide variety of sports related terms, including team names, player positions, and competition names

    oai_token-act-pair · 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
    findpost
    -0.63
    iastes
    -0.60
    ✨:
    -0.50
    ագրություններ
    -0.50
    -------
    -0.50
    WEBPACK
    -0.50
     Signalez
    -0.48
     שוליים
    -0.47
     contextLoads
    -0.47
    ContentAlignment
    -0.47
    POSITIVE LOGITS
     nahilalakip
    0.61
     surla
    0.59
    存于互联网档案馆
    0.58
    onets
    0.54
    曖昧さ回避
    0.54
    POSURE
    0.50
    спонд
    0.50
    iedz
    0.50
    asin
    0.49
    ilist
    0.49
    Activations Density 0.792%

    No Known Activations