© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126921
    Prev
    Next
    INDEX
    Explanations

    F chord, math, m notation

    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_3_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
     (
    0.86
    ER
    0.82
    OL
    0.73
    حية
    0.71
    ك
    0.70
    াক
    0.69
    ্যান্ড
    0.66
    িকে
    0.64
     Lá
    0.63
    LLI
    0.61
    POSITIVE LOGITS
    m
    0.96
    지
    0.94
    d
    0.90
    어
    0.75
     paio
    0.70
    mf
    0.66
    ם
    0.66
    ৮
    0.65
    져
    0.65
    mari
    0.64
    Activations Density 0.001%

    No Known Activations