© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62739
    Prev
    Next
    INDEX
    Explanations

    feeding on

    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_11_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
    waste
    0.63
    uberculosis
    0.58
    testing
    0.57
    s
    0.57
    telling
    0.57
    ventana
    0.56
     Рабо
    0.55
    task
    0.55
     nCurrent
    0.55
    sample
    0.54
    POSITIVE LOGITS
     vowed
    0.67
    گ
    0.62
    <0x93>
    0.59
     WIFI
    0.59
    ção
    0.58
     گ
    0.57
    ونو
    0.56
     stirred
    0.55
    <0xB2>
    0.55
     περι
    0.55
    Activations Density 0.020%

    No Known Activations