© 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. 113282
    Prev
    Next
    INDEX
    Explanations

    voltage drops

    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
    ح
    1.76
    ك
    1.76
    ку
    1.63
    و
    1.59
    ના
    1.55
    ма
    1.43
    ні
    1.43
    ק
    1.41
    いた
    1.40
    ری
    1.34
    POSITIVE LOGITS
     for
    1.66
    (
    1.62
    is
    1.30
     from
    1.28
    :
    1.23
     fifth
    1.22
    ↵
    1.20
    -
    1.15
     y
    1.13
     K
    1.11
    Activations Density 0.004%

    No Known Activations