© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62751
    Prev
    Next
    INDEX
    Explanations

    Twitch and wrist actions

    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_2_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
    ك
    1.77
    ش
    1.73
    на
    1.71
    نا
    1.53
    ند
    1.48
    ح
    1.44
    ุ
    1.41
    س
    1.34
    ні
    1.33
    ח
    1.33
    POSITIVE LOGITS
    (
    1.27
    েও
    1.14
     reorgan
    1.12
    H
    1.10
    な
    1.10
    ﺽ
    1.09
    勮
    1.09
    ᱐
    1.04
    ຮັບ
    0.99
    K
    0.98
    Activations Density 0.005%

    No Known Activations