© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109271
    Prev
    Next
    INDEX
    Explanations

    creepy or investigations

    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_1_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
    et
    1.66
    c
    1.63
    t
    1.61
    r
    1.59
    an
    1.41
    d
    1.38
    ى
    1.36
    dollars
    1.32
    s
    1.32
    b
    1.28
    POSITIVE LOGITS
    1.53
     a
    1.18
    ING
    1.16
     is
    1.03
    .
    0.96
    จะ
    0.96
     i
    0.96
     de
    0.95
    Ս
    0.92
     ri
    0.90
    Activations Density 0.003%

    No Known Activations