© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142239
    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_0_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
    elen
    0.47
    ifier
    0.46
    eville
    0.46
    eling
    0.45
    elling
    0.45
     ow
    0.44
     Urban
    0.43
    ʃ
    0.42
     I
    0.42
    слов
    0.42
    POSITIVE LOGITS
    laquo
    0.45
    CA
    0.44
    uot
    0.44
    ้า
    0.43
    ഹ്ലാ
    0.42
     Labrenzia
    0.42
     உதவுக
    0.41
    NGC
    0.41
    NgModule
    0.40
    ڈنگ
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.