© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30458
    Prev
    Next
    INDEX
    Explanations

    filter followed by lambda or condition

    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_10_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
     絵
    0.55
     ၁
    0.55
     editorials
    0.55
     ϕ
    0.55
    ラの
    0.53
    <0x82>
    0.52
     Α
    0.52
     textbooks
    0.52
     Со
    0.52
     manuals
    0.50
    POSITIVE LOGITS
    3
    0.57
    2
    0.54
     materialize
    0.51
    tn
    0.50
    5
    0.47
    to
    0.46
    9
    0.46
    mäßig
    0.45
    February
    0.45
    קס
    0.44
    Activations Density 0.033%

    No Known Activations