© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78107
    Prev
    Next
    INDEX
    Explanations

    wurde (past passive)

    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_0_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
    1.53
     ampli
    1.46
     in
    1.45
     interdit
    1.27
     instal
    1.19
     offent
    1.19
    在
    1.18
     aval
    1.14
     insc
    1.14
    ه
    1.13
    POSITIVE LOGITS
    л
    2.00
    ל
    1.50
    dır
    1.45
    며
    1.27
    ل
    1.26
    dan
    1.25
    r
    1.21
    ón
    1.18
    з
    1.16
    ك
    1.13
    Activations Density 0.000%

    No Known Activations