© 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. 19832
    Prev
    Next
    INDEX
    Explanations

    "attention mechanism," "self-care," "ideal for submission"

    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
             
    0.28
    Signal
    0.27
    "},
    0.26
    Assistant
    0.26
    City
    0.25
    이죠
    0.25
    assistant
    0.25
    Param
    0.25
    "};
    0.25
    $:
    0.25
    POSITIVE LOGITS
     incorporates
    0.29
     Reduces
    0.28
     Calculates
    0.28
    asi
    0.27
     ইনি
    0.25
     ইহাতে
    0.25
     complies
    0.25
     \%
    0.25
     Removes
    0.25
     Classifier
    0.24
    Activations Density 0.027%

    No Known Activations