© 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. 122328
    Prev
    Next
    INDEX
    Explanations

    signs and XIII

    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
    는
    0.82
    は
    0.77
    是
    0.71
    ید
    0.69
     раство
    0.62
    は約
    0.62
    rals
    0.61
    ről
    0.61
    h
    0.61
    ون
    0.60
    POSITIVE LOGITS
    '
    0.91
    ↵
    0.73
     for
    0.70
    EL
    0.69
    UM
    0.67
    ?
    0.62
    SE
    0.62
    م
    0.60
    ST
    0.58
    HT
    0.58
    Activations Density 0.000%

    No Known Activations