© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138902
    Prev
    Next
    INDEX
    Explanations

    hearing or sound

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     prou
    0.41
     অনুপ
    0.41
     minh
    0.38
    앗
    0.38
     flo
    0.38
     अनुप
    0.38
     arg
    0.37
     bö
    0.37
    inete
    0.37
     rost
    0.37
    POSITIVE LOGITS
    Hear
    0.45
    doFilter
    0.44
     chí
    0.41
    ås
    0.39
     Hear
    0.39
     ears
    0.38
     แก้
    0.38
    ‵
    0.38
    Highlights
    0.37
    Nearly
    0.37
    Activations Density 0.000%

    No Known Activations