© 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. 88796
    Prev
    Next
    INDEX
    Explanations

    alphabetize my

    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
    (
    0.49
    に行って
    0.46
     sondern
    0.46
    Adap
    0.45
     calmed
    0.45
    🤦
    0.45
     legalized
    0.44
     downright
    0.44
     behavior
    0.43
     interrupted
    0.43
    POSITIVE LOGITS
    ミ
    0.66
    リ
    0.64
    ਨਾ
    0.57
    キ
    0.56
    दि
    0.54
    ニ
    0.54
    ری
    0.53
    ри
    0.51
    ナ
    0.51
    ನಿ
    0.50
    Activations Density 0.000%

    No Known Activations