© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 219118
    Prev
    Next
    INDEX
    Explanations

    hooks and questions

    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_16_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
     mental
    0.51
    گ
    0.47
    hato
    0.44
    Emma
    0.44
    uku
    0.44
    utus
    0.43
    Mental
    0.42
     sute
    0.42
     side
    0.42
    European
    0.42
    POSITIVE LOGITS
    >;</
    0.58
     ҡ
    0.57
    <unused2138>
    0.57
     ולא
    0.54
     忄
    0.54
    ₮
    0.53
     как
    0.52
     съ
    0.52
     ohne
    0.52
     выбира
    0.51
    Activations Density 0.037%

    No Known Activations