© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80827
    Prev
    Next
    INDEX
    Explanations

    beginnings of words

    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_0_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
    the
    1.04
    V
    1.00
    J
    1.00
    an
    1.00
    on
    0.95
    r
    0.89
    st
    0.89
    p
    0.86
    Q
    0.84
    us
    0.84
    POSITIVE LOGITS
     μεγά
    0.93
    ми
    0.90
    ي
    0.90
    ка
    0.89
     garantías
    0.88
     adecuadas
    0.88
    ﻦ
    0.86
    شي
    0.85
    لي
    0.82
    مين
    0.81
    Activations Density 0.000%

    No Known Activations