© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14657
    Prev
    Next
    INDEX
    Explanations

    capitalized names

    oai_token-act-pair · gemini-2.0-flash

    technical terms or coding syntax

    np_token-act-pair-logits · gpt-4o-mini

    names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Sortie
    -0.48
     sulf
    -0.47
     punch
    -0.47
    లాలు
    -0.47
     sy
    -0.46
    Produzione
    -0.46
     syn
    -0.45
     lyn
    -0.44
     qx
    -0.44
     Syn
    -0.43
    POSITIVE LOGITS
    tvguidetime
    0.92
     AssemblyCulture
    0.76
    DoubleQuotes
    0.73
    aarrggbb
    0.69
    StructEnd
    0.65
     kasarigan
    0.64
    DockStyle
    0.64
    ########.
    0.64
    rrggbb
    0.62
    ViewImports
    0.62
    Activations Density 0.812%

    No Known Activations