© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54150
    Prev
    Next
    INDEX
    Explanations

    version constraint "~>"

    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_31_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
    uez
    0.39
     دهد
    0.38
    陏
    0.38
    摂
    0.38
    ôme
    0.37
     Hospice
    0.37
    odie
    0.36
     pseud
    0.36
    өн
    0.36
    pseudo
    0.36
    POSITIVE LOGITS
     Michelin
    0.38
    トレー
    0.37
     (…)
    0.37
     […]
    0.37
    […]
    0.37
    ্বা
    0.36
     rán
    0.36
    flake
    0.35
     руках
    0.35
     hạt
    0.35
    Activations Density 0.000%

    No Known Activations