© 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-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170591
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gracias
    0.18
    ドリンク
    0.17
    OR
    0.16
    Recipes
    0.16
    声
    0.16
    <unused21>
    0.15
     Dropout
    0.15
     haircuts
    0.15
    \{
    0.15
    thanks
    0.15
    POSITIVE LOGITS
    setDate
    0.17
     Nav
    0.16
     ވަ
    0.16
     находя
    0.15
     Instal
    0.15
    ichtung
    0.14
    தைத்
    0.14
    ">{{
    0.14
     предполагает
    0.14
    溃
    0.14
    Activations Density 0.000%

    No Known Activations