© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31149
    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_7_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
     are
    0.69
     be
    0.67
    ik
    0.62
    ↵↵
    0.58
    ore
    0.56
     $\
    0.56
    aka
    0.55
     the
    0.55
    }\
    0.55
     had
    0.55
    POSITIVE LOGITS
    một
    0.63
    y
    0.59
    you
    0.58
    và
    0.56
    cję
    0.55
    ला
    0.55
    ，
    0.54
     établ
    0.53
    अनुसूचित
    0.52
    ಯೇ
    0.52
    Activations Density 0.000%

    No Known Activations