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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7283
    Prev
    Next
    INDEX
    Explanations

    the combination of formatting characters and words used in comments and legal documents

    oai_token-act-pair · gemini-2.0-flash

    Code-related

    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
     I
    -0.56
     '
    -0.56
     
    -0.54
     "
    -0.47
     ',
    -0.44
     '.
    -0.44
    ?'
    -0.43
     comment
    -0.43
     ';
    -0.42
     As
    -0.42
    POSITIVE LOGITS
     ویکی‌پدیای
    0.93
    +#+
    0.85
     HasFactory
    0.81
     المعيارى
    0.81
    ViewImports
    0.79
    日閲覧
    0.79
    migrationBuilder
    0.79
     ddelweddau
    0.76
    ScopeManager
    0.76
    AddTagHelper
    0.76
    Activations Density 14.229%

    No Known Activations