© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258273
    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_22_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
     Havana
    0.44
     dashing
    0.44
     rusk
    0.44
    日付
    0.44
     provoc
    0.43
    囩
    0.43
    铤
    0.42
     čin
    0.42
     Cuban
    0.42
    quillo
    0.42
    POSITIVE LOGITS
    ᇁ
    0.46
    insch
    0.43
    वाई
    0.42
    Aj
    0.41
    Broad
    0.41
    ANZ
    0.40
     माल
    0.39
    our
    0.39
    U
    0.39
    Unser
    0.39
    Activations Density 0.000%

    No Known Activations