© 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. 9188
    Prev
    Next
    INDEX
    Explanations

    citations in legal opinions or scientific papers

    oai_token-act-pair · gemini-2.0-flash

    Academic/legal citations

    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
     American
    -0.64
    American
    -0.63
    currentColor
    -0.62
     NSCoder
    -0.60
     Amer
    -0.59
    Thursday
    -0.58
     Thursday
    -0.56
     Wednesday
    -0.56
     num
    -0.56
    Department
    -0.56
    POSITIVE LOGITS
     typelib
    0.51
    PHPExcel
    0.51
     Besoin
    0.50
    ywna
    0.49
     acús
    0.49
    setVerticalGroup
    0.48
     aérea
    0.47
    gnąć
    0.47
     littéraire
    0.46
    giène
    0.46
    Activations Density 6.339%

    No Known Activations