© 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. 9179
    Prev
    Next
    INDEX
    Explanations

    food names, especially cheese and cheeseburgers

    oai_token-act-pair · 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
    addCriterion
    -0.69
    ErrUnexpectedEOF
    -0.59
     ComVisible
    -0.59
     صوتيه
    -0.59
     CHE
    -0.59
    verwijspagina
    -0.59
    WebElementEntity
    -0.57
    QMetaType
    -0.57
    endpush
    -0.57
    δου
    -0.56
    POSITIVE LOGITS
    GEBURTSDATUM
    0.49
    XmlType
    0.47
     Wä
    0.43
    ológ
    0.43
     bulb
    0.42
    IContainer
    0.42
     Pferde
    0.41
    saraba
    0.41
     ź
    0.40
    Barg
    0.40
    Activations Density 2.158%

    No Known Activations