© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10126
    Prev
    Next
    INDEX
    Explanations

    words ending in specific suffixes, prefixes, or other non-letter symbols

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    aarrggbb
    -0.85
    <bos>
    -0.81
    migrationBuilder
    -0.69
    DockStyle
    -0.66
    oredCriteria
    -0.66
     ?>">
    -0.65
    ADELPHIA
    -0.64
    ahal
    -0.64
    ³)
    -0.61
     препратки
    -0.61
    POSITIVE LOGITS
    RenderAtEndOf
    0.56
    didSet
    0.54
    ControllerAdvice
    0.51
    RetentionPolicy
    0.46
    ={`/
    0.45
    Cubit
    0.45
    ölk
    0.44
    ทย
    0.44
    TagMode
    0.44
     समीक्षक
    0.44
    Activations Density 4.325%

    No Known Activations