© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 209572
    Prev
    Next
    INDEX
    Explanations

    list of items with quantities

    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_25_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
     prepared
    0.26
    prepared
    0.25
     perceived
    0.24
     каждом
    0.23
     каждым
    0.23
    +\
    0.23
     each
    0.22
    <strong>
    0.22
     marketed
    0.22
    Each
    0.22
    POSITIVE LOGITS
     Pg
    0.27
     לת
    0.25
    новниш
    0.24
    btnUn
    0.24
     LMP
    0.24
     αφ
    0.24
    γκ
    0.24
    Ꮔ
    0.24
    屣
    0.24
    шкан
    0.23
    Activations Density 0.042%

    No Known Activations