© 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. 113331
    Prev
    Next
    INDEX
    Explanations

    Prolog SWI

    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
    1
    1.46
    2
    1.32
    5
    1.30
     and
    1.22
    9
    1.20
    6
    1.20
    AI
    1.16
     I
    1.12
    were
    1.11
    is
    1.09
    POSITIVE LOGITS
     desolate
    0.95
     don
    0.93
     demonstrate
    0.93
     it
    0.89
     an
    0.88
    o
    0.86
     sickening
    0.86
     succumb
    0.86
     certific
    0.85
     brighten
    0.83
    Activations Density 0.001%

    No Known Activations