© 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. 1343
    Prev
    Next
    INDEX
    Explanations

    code snippets and structured data, particularly with hyphens, underscores, and punctuation

    oai_token-act-pair · gemini-2.0-flash

    French words

    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
     rooms
    -0.95
     beds
    -0.88
     notes
    -0.88
     breeds
    -0.87
     documents
    -0.87
     bodies
    -0.87
     pages
    -0.86
     seats
    -0.85
     posts
    -0.85
     points
    -0.84
    POSITIVE LOGITS
     épaules
    0.94
     vœux
    0.84
     négociations
    0.78
     vérit
    0.77
     oreilles
    0.75
     lèvres
    0.75
     genoux
    0.75
     touristes
    0.74
     investissements
    0.73
     renseignements
    0.73
    Activations Density 7.080%

    No Known Activations