© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31426
    Prev
    Next
    INDEX
    Explanations

    sensory descriptions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    抛
    0.34
    நப
    0.31
    镌
    0.31
    రూ
    0.30
     sleeves
    0.30
    ↵
    0.30
     floats
    0.29
     bottle
    0.29
     rags
    0.29
     evin
    0.29
    POSITIVE LOGITS
     прият
    0.38
     angene
    0.34
    прият
    0.33
     камера
    0.33
     sắt
    0.32
    餡
    0.32
     приятно
    0.32
     Investigación
    0.31
    دم
    0.31
    ল্যান্ডের
    0.31
    Activations Density 0.046%

    No Known Activations