© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34185
    Prev
    Next
    INDEX
    Explanations

    um, umn, umna 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_7_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
    ٢
    1.13
    IS
    1.06
    ер
    0.99
    وف
    0.93
    І
    0.92
    𝐈
    0.89
    ৫
    0.87
    FFA
    0.86
    綵
    0.84
    K
    0.84
    POSITIVE LOGITS
    se
    1.45
    f
    1.38
    t
    1.33
    d
    1.28
    re
    1.27
    le
    1.20
    ve
    1.18
    ll
    1.18
    s
    1.17
    v
    1.16
    Activations Density 0.000%

    No Known Activations