© 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. 8040
    Prev
    Next
    INDEX
    Explanations

    references to academic publications

    oai_token-act-pair · gemini-2.0-flash

    words with special characters or symbols

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

    academic citations

    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
    AutoresizingMask
    -0.73
     ModelExpression
    -0.69
     AssemblyCompany
    -0.66
     beginnetje
    -0.64
     ),
    -0.63
    UnknownFieldSet
    -0.63
    ніципалі
    -0.60
     CreateTagHelper
    -0.59
    :][
    -0.59
    UnsafeEnabled
    -0.59
    POSITIVE LOGITS
     tæ
    0.53
    acate
    0.48
    itori
    0.46
     οδ
    0.46
    ⓧ
    0.45
     przewod
    0.45
     mélanger
    0.45
     getrock
    0.44
     مشين
    0.44
     réfugi
    0.44
    Activations Density 0.696%

    No Known Activations