© 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. 8428
    Prev
    Next
    INDEX
    Explanations

    code- or math-related documentation

    oai_token-act-pair · gemini-2.0-flash

    division

    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
     rantai
    -0.66
     række
    -0.62
     scolaires
    -0.60
    verhältnis
    -0.54
     eixo
    -0.53
     gebunden
    -0.52
     scolaire
    -0.52
     balón
    -0.52
     mixture
    -0.52
    mises
    -0.51
    POSITIVE LOGITS
    Personensuche
    0.70
    rawDesc
    0.60
    batore
    0.60
    BITE
    0.58
    extAlignment
    0.57
    下载附件
    0.57
    .")
    0.57
    orghini
    0.56
    GraphicsUnit
    0.55
    )’
    0.55
    Activations Density 37.165%

    No Known Activations