© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57832
    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_11_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
     ($
    0.51
     raced
    0.47
     race
    0.46
     ayrıca
    0.45
     races
    0.44
     strapped
    0.44
     pulled
    0.44
     następnie
    0.44
     valida
    0.42
     (
    0.42
    POSITIVE LOGITS
    靔
    0.52
    ré
    0.51
    hbs
    0.51
     amaze
    0.49
     Varan
    0.49
    刚
    0.49
    الان
    0.47
     गहराई
    0.47
    стье
    0.47
    h
    0.47
    Activations Density 0.000%

    No Known Activations