© 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. 57569
    Prev
    Next
    INDEX
    Explanations

    translates and code suggestions

    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
     この
    1.13
     お
    1.09
     এরই
    1.01
     അവർ
    1.00
     此
    0.98
     か
    0.97
     άλλ
    0.95
    ोरेशन
    0.95
     마
    0.95
     오는
    0.95
    POSITIVE LOGITS
    the
    1.82
    an
    1.48
    as
    1.27
    し
    1.26
    0
    1.23
    ного
    1.22
    LY
    1.16
    은
    1.15
    r
    1.11
    ю
    1.10
    Activations Density 0.004%

    No Known Activations