© 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. 108261
    Prev
    Next
    INDEX
    Explanations

    ey sequences

    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
    '
    1.30
    ’
    1.19
    ”)
    0.84
    spiele
    0.84
    ப
    0.84
    strated
    0.83
    립니다
    0.82
    '،
    0.81
    ಮ
    0.80
    აქ
    0.77
    POSITIVE LOGITS
     and
    1.30
    í
    1.12
    ia
    1.10
    é
    1.09
     as
    1.03
    ü
    1.03
    z
    0.95
    ं
    0.94
    ル
    0.93
    st
    0.91
    Activations Density 0.000%

    No Known Activations