© 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. 162459
    Prev
    Next
    INDEX
    Explanations

    intrinsically, intrigue, intruding

    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
    Not in Any Lists

    No Comments

    Negative Logits
    t
    1.36
    我
    1.06
    On
    1.05
    offs
    1.02
     commenc
    1.02
    Ι
    1.00
     on
    1.00
     mortars
    0.97
    l
    0.96
    އ
    0.96
    POSITIVE LOGITS
    ong
    1.31
    ל
    1.22
    ة
    1.20
    ва
    1.16
    ла
    1.16
    ing
    1.15
    gebaut
    1.13
    om
    1.13
    ol
    1.11
    $
    1.10
    Activations Density 0.001%

    No Known Activations