© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214234
    Prev
    Next
    INDEX
    Explanations

    Soseki, Sek, se, ze

    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_5_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
    a
    1.52
    p
    1.48
    the
    1.46
    of
    1.28
    ных
    1.22
    ro
    1.14
    to
    1.13
    j
    1.13
    ting
    1.09
    ts
    1.07
    POSITIVE LOGITS
    >
    0.95
    ৯
    0.95
     Royaume
    0.91
    را
    0.89
    یی
    0.88
    DEBUGFS
    0.88
     //.
    0.86
    あれば
    0.85
    iz
    0.83
    šti
    0.83
    Activations Density 0.000%

    No Known Activations