© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13335
    Prev
    Next
    INDEX
    Explanations

    scaling, exploding gradients, quantization

    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_15_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
    G
    0.57
    /
    0.56
    '
    0.53
     weaker
    0.52
     lines
    0.50
     G
    0.50
    UF
    0.50
    A
    0.50
    -
    0.50
    IC
    0.49
    POSITIVE LOGITS
     グレー
    0.54
    럇
    0.53
    etown
    0.52
    ርስ
    0.51
    мець
    0.50
     MinMaxScaler
    0.50
    രേ
    0.50
     Veamos
    0.49
     автоматтары
    0.49
    άνει
    0.48
    Activations Density 0.058%

    No Known Activations