© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157322
    Prev
    Next
    INDEX
    Explanations

    endure, evaluation, surety, music, Thai/Vietnamese phrases

    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_2_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
    4
    1.32
    3
    1.26
     aument
    1.23
    x
    1.13
    il
    1.12
    2
    1.12
    ہ
    1.10
     руководство
    1.08
     I
    1.06
     envi
    1.03
    POSITIVE LOGITS
     was
    1.25
    ها
    1.22
    don
    1.07
     that
    1.06
    ม
    1.05
    an
    1.01
    ens
    1.01
    netic
    0.98
    larından
    0.97
    ln
    0.97
    Activations Density 0.000%

    No Known Activations