© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2742
    Prev
    Next
    INDEX
    Explanations

    hyphenated words and words within legal documents or academic papers, potentially associated with legal jargon.

    oai_token-act-pair · gemini-2.0-flash

    -

    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
    <bos>
    -0.55
    ніципалі
    -0.50
    Tracklist
    -0.50
    Smarty
    -0.45
    hips
    -0.44
    encodeWith
    -0.44
    Soundtrack
    -0.44
    Cursors
    -0.43
    AGES
    -0.43
    ThroughAttribute
    -0.43
    POSITIVE LOGITS
     tartalomajánló
    0.64
    Bibliograf
    0.53
    respondent
    0.52
    ommen
    0.51
    stående
    0.50
    aap
    0.49
     françaises
    0.49
    Predecesor
    0.48
    endphp
    0.48
     Cesar
    0.48
    Activations Density 19.770%

    No Known Activations