© 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. 292
    Prev
    Next
    INDEX
    Explanations

    frequent words and discourse markers such as "so", "are", "lot", "of", "a", and question markers.

    oai_token-act-pair · gemini-2.0-flash

    conversational filler

    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
     doInBackground
    -0.57
     investissements
    -0.56
     boî
    -0.56
     épaules
    -0.54
     églises
    -0.50
     lèvres
    -0.48
     bénéfices
    -0.47
     modalités
    -0.47
     autorités
    -0.47
    Hochspringen
    -0.46
    POSITIVE LOGITS
    noons
    0.77
    boys
    0.69
    eds
    0.68
    icals
    0.68
     dads
    0.68
     pets
    0.66
    ilets
    0.65
     boys
    0.64
    totals
    0.64
    hets
    0.64
    Activations Density 14.821%

    No Known Activations