© 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. 85924
    Prev
    Next
    INDEX
    Explanations

    naratriptan, Naoto Kan

    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
     a
    0.97
    v
    0.96
    ร
    0.92
     o
    0.88
    ne
    0.82
     be
    0.77
     to
    0.77
    ि
    0.76
     r
    0.75
    ่
    0.73
    POSITIVE LOGITS
    ak
    0.97
    es
    0.75
    ت
    0.75
    am
    0.74
    つ
    0.73
    Más
    0.72
    eers
    0.72
    కు
    0.71
    The
    0.70
    ađ
    0.70
    Activations Density 0.000%

    No Known Activations