© 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. 14912
    Prev
    Next
    INDEX
    Explanations

    snippets from various languages

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    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
     démocratie
    -0.68
     alimentaire
    -0.67
     mauvaises
    -0.65
     sagesse
    -0.65
     sementes
    -0.65
     fumée
    -0.64
     stratégique
    -0.63
    +#+#
    -0.63
     polaire
    -0.62
     suprême
    -0.60
    POSITIVE LOGITS
    latego
    0.75
     creemos
    0.64
     trattano
    0.64
    Esperamos
    0.60
    raszamy
    0.59
     creen
    0.59
     decidieron
    0.59
     ergeben
    0.59
     recomendamos
    0.58
     хотелось
    0.57
    Activations Density 3.300%

    No Known Activations