© 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. 6957
    Prev
    Next
    INDEX
    Explanations

    scientific language around measurement and prediction

    oai_token-act-pair · gemini-2.0-flash

    technical documents

    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
     chang
    -0.84
     servic
    -0.80
     mak
    -0.79
    chang
    -0.78
     oper
    -0.76
     marke
    -0.74
     fil
    -0.74
     wor
    -0.73
     tra
    -0.73
     bea
    -0.67
    POSITIVE LOGITS
     vectorielles
    0.97
     spéciaux
    0.97
     normaux
    0.96
     juridiques
    0.95
     scolaires
    0.95
     démocr
    0.93
     termica
    0.92
     supérieures
    0.91
     prisonniers
    0.90
     électroniques
    0.90
    Activations Density 1.027%

    No Known Activations