© 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. 45928
    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
    ivité
    0.47
    cheidet
    0.46
    ちは
    0.45
    েলে
    0.44
    3
    0.44
     গুজ
    0.43
     φι
    0.42
    ogical
    0.42
     কারা
    0.42
     кры
    0.42
    POSITIVE LOGITS
    Dod
    0.46
     Vương
    0.44
    Player
    0.42
     Aubrey
    0.42
    \")
    0.42
    Poster
    0.42
    Password
    0.41
    幂
    0.41
     Poster
    0.41
     Hopefully
    0.41
    Activations Density 0.000%

    No Known Activations