© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232881
    Prev
    Next
    INDEX
    Explanations

    condition of

    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_6_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
     you
    1.17
     at
    1.06
    -
    0.98
    یل
    0.98
    ன
    0.98
     rulemaking
    0.96
     that
    0.95
    ิ
    0.91
     speciali
    0.91
     partnering
    0.89
    POSITIVE LOGITS
    p
    1.59
    s
    1.55
    us
    1.41
    k
    1.31
    z
    1.23
    j
    1.23
    g
    1.14
    m
    1.13
    ak
    1.11
    的
    1.11
    Activations Density 0.000%

    No Known Activations