© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135496
    Prev
    Next
    INDEX
    Explanations

    video encoding and decoding

    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_6_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    '
    1.20
    ent
    1.07
    t
    1.00
    ↵
    0.94
    al
    0.92
    ?
    0.92
     of
    0.86
    ah
    0.86
     importar
    0.83
    ان
    0.82
    POSITIVE LOGITS
    I
    0.93
    s
    0.92
    A
    0.88
    ો
    0.83
    ступ
    0.76
    。"
    0.75
    AO
    0.75
    ші
    0.73
    F
    0.73
    വശ
    0.72
    Activations Density 0.000%

    No Known Activations