© 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. 67798
    Prev
    Next
    INDEX
    Explanations

    mushrooms

    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
     skipping
    0.45
    ूनी
    0.40
     skip
    0.40
     cathode
    0.37
     skips
    0.37
     skipped
    0.37
    头的
    0.37
    <unused1>
    0.37
     跳
    0.36
    覇
    0.36
    POSITIVE LOGITS
     Hy
    0.86
     hy
    0.85
    Hy
    0.83
    hy
    0.69
    mushroom
    0.66
     Mushroom
    0.66
     mushrooms
    0.64
     mushroom
    0.64
     Myc
    0.62
    fung
    0.61
    Activations Density 0.024%

    No Known Activations