© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2548
    Prev
    Next
    INDEX
    Explanations

    code-related tokens within a programming language.

    oai_token-act-pair · gemini-2.0-flash

    Foreign language phrases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     houſe
    -0.87
     ſche
    -0.75
    parsedMessage
    -0.73
     fevere
    -0.73
    InjectAttribute
    -0.72
     Administrativna
    -0.71
    DeleteBehavior
    -0.71
    saraba
    -0.69
     Houſe
    -0.69
    ſelf
    -0.69
    POSITIVE LOGITS
     вот
    0.42
    Voici
    0.38
     I
    0.36
    :=\
    0.36
     merken
    0.36
    Conclusão
    0.36
    Вот
    0.35
     désolés
    0.35
    Sure
    0.35
    genza
    0.35
    Activations Density 2.512%

    No Known Activations