© 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. 107714
    Prev
    Next
    INDEX
    Explanations

    lobster

    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
    l
    1.74
    an
    1.72
    a
    1.70
    ه
    1.66
    et
    1.59
    s
    1.55
    in
    1.52
    ur
    1.42
    i
    1.35
    er
    1.34
    POSITIVE LOGITS
    ве
    1.07
     θέση
    1.05
     в
    0.98
     неко
    0.97
    annya
    0.93
     consape
    0.92
    が存在
    0.91
     função
    0.90
     числе
    0.89
     ау
    0.89
    Activations Density 0.001%

    No Known Activations