© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133982
    Prev
    Next
    INDEX
    Explanations

    masked or placeholder string

    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_1_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
    t
    1.36
    h
    1.36
    m
    1.29
    to
    1.27
     to
    1.16
    ور
    1.15
    خ
    1.12
    ش
    1.11
    τη
    1.07
    c
    1.05
    POSITIVE LOGITS
    '
    0.93
     Министер
    0.91
    ’
    0.91
     squadron
    0.89
    üyor
    0.88
     மன்ற
    0.88
     mieszkań
    0.88
    $
    0.86
    ümler
    0.84
    ía
    0.82
    Activations Density 0.000%

    No Known Activations