© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132929
    Prev
    Next
    INDEX
    Explanations

    secure network, data, communication

    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
    s
    1.50
    '
    1.50
    in
    1.39
    t
    1.30
    the
    1.25
    \
    1.23
    li
    1.20
    eling
    1.20
    *
    1.18
    ts
    1.17
    POSITIVE LOGITS
     ၁
    1.04
     is
    1.01
     godine
    0.98
     menyatakan
    0.96
     nineteen
    0.92
     Consultado
    0.91
     mengaku
    0.90
    ಾನೂ
    0.90
     ชอบ
    0.89
     tanggal
    0.88
    Activations Density 0.004%

    No Known Activations