© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 221219
    Prev
    Next
    INDEX
    Explanations

    separating lists of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     indicates
    0.31
    まだまだ
    0.31
    routeProvider
    0.31
     recalls
    0.30
    懐
    0.30
    覚え
    0.29
     recalled
    0.29
     Medicare
    0.29
    recall
    0.29
     җ
    0.29
    POSITIVE LOGITS
     UTIL
    0.32
     बढ़ाकर
    0.32
    げて
    0.30
    独自の
    0.30
     तारीफ
    0.30
     veine
    0.30
     toJson
    0.30
    ನ್ನ
    0.29
    జర్
    0.29
    ներ
    0.29
    Activations Density 0.001%

    No Known Activations