© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164182
    Prev
    Next
    INDEX
    Explanations

    button type="submit"

    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
     h
    0.46
    숍
    0.38
     dome
    0.38
     houses
    0.38
    ſed
    0.37
    शांत
    0.37
    ফি
    0.36
     han
    0.36
    QN
    0.36
     taas
    0.36
    POSITIVE LOGITS
     মিথ
    0.40
     submit
    0.38
     улы
    0.37
     '>
    0.35
     submits
    0.35
    submit
    0.34
    skii
    0.34
     থাকছে
    0.34
    :][
    0.34
    حدث
    0.34
    Activations Density 0.003%

    No Known Activations