© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4163
    Prev
    Next
    INDEX
    Explanations

    information related to sports leagues, teams, and schedules

    oai_token-act-pair · gemini-2.0-flash

    Niche topics

    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
    endphp
    -0.71
    principalTable
    -0.69
    awtextra
    -0.64
    AndEndTag
    -0.63
     '\\;'
    -0.60
    Diwedd
    -0.55
     InputDecoration
    -0.53
    SharedCtor
    -0.52
     censiti
    -0.50
    nezeu
    -0.50
    POSITIVE LOGITS
    onActivityResult
    0.56
     skj
    0.54
    HandlerContext
    0.52
    BIOGRAPHY
    0.50
     Transplant
    0.48
    athy
    0.48
    invokeLater
    0.48
    Hob
    0.47
    hoga
    0.47
    youts
    0.47
    Activations Density 3.179%

    No Known Activations