© 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. 7841
    Prev
    Next
    INDEX
    Explanations

    mentions of specific benchmark datasets and their features, especially in the context of performance analysis and technical comparisons

    oai_token-act-pair · gemini-2.0-flash

    specific dataset identifiers or technical terms related to data processing

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

    datasets

    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
    +#+#
    -0.73
    лактика
    -0.60
    findpost
    -0.57
    /***/
    -0.56
     kautta
    -0.55
    fficients
    -0.54
     Vermögen
    -0.54
     Lázaro
    -0.54
    transQ
    -0.54
    ksesta
    -0.53
    POSITIVE LOGITS
    pan
    0.48
     NUKAT
    0.47
    torie
    0.47
    Jit
    0.47
     pano
    0.47
     agra
    0.46
    Diweddarwch
    0.46
    ued
    0.46
    jah
    0.46
     JpaRepository
    0.45
    Activations Density 4.614%

    No Known Activations