© 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. 206779
    Prev
    Next
    INDEX
    Explanations

    th 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
    ation
    1.18
    ate
    1.02
    ings
    1.00
    ierung
    1.00
    chen
    0.98
    ments
    0.97
    0.93
    istle
    0.92
    sen
    0.91
    oc
    0.89
    POSITIVE LOGITS
    ח
    1.59
    ור
    1.40
    ک
    1.28
    ه
    1.22
    ہ
    1.22
    ה
    1.22
    ס
    1.19
    ז
    1.18
    치
    1.17
    ست
    1.16
    Activations Density 0.000%

    No Known Activations