© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232548
    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_32_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
     técnicos
    0.41
    边
    0.38
    Attachment
    0.38
    краё
    0.37
     краё
    0.36
    ՝
    0.36
     shaved
    0.36
     erk
    0.35
     첨
    0.35
    気づ
    0.35
    POSITIVE LOGITS
    परेट
    0.46
     scaling
    0.44
     railing
    0.40
    aktif
    0.39
    娉
    0.39
     pitan
    0.38
    getActive
    0.37
    ازی
    0.37
     landfall
    0.37
    getBase
    0.37
    Activations Density 0.000%

    No Known Activations