© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229420
    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_57_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
     الب
    0.53
     הב
    0.53
     ahu
    0.51
     B
    0.44
    ercises
    0.40
    amphetamine
    0.38
     존
    0.38
     बी
    0.38
    الب
    0.38
     మార్
    0.37
    POSITIVE LOGITS
    Gro
    0.80
     הג
    0.78
     Gro
    0.78
     GRO
    0.77
    GRO
    0.73
    G
    0.73
     G
    0.68
     Groove
    0.67
    Gross
    0.66
     Gross
    0.65
    Activations Density 0.000%

    No Known Activations