© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 216032
    Prev
    Next
    INDEX
    Explanations

    allergies

    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_5_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
     in
    1.16
    <0x80>
    1.05
    pressing
    1.02
    ib
    1.00
    boosting
    0.98
    ans
    0.92
    ння
    0.90
    quen
    0.90
    s
    0.90
    ressive
    0.88
    POSITIVE LOGITS
    ב
    1.82
    ES
    1.63
    ী
    1.51
    ה
    1.47
    ING
    1.39
    ת
    1.37
    ک
    1.32
    AK
    1.30
    OH
    1.29
    কে
    1.28
    Activations Density 0.001%

    No Known Activations