© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35756
    Prev
    Next
    INDEX
    Explanations

    acronyms and codes

    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_7_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
    ان
    0.34
    ت
    0.34
    ل
    0.31
    و
    0.30
    ת
    0.30
    an
    0.28
    ל
    0.28
    י
    0.27
    ק
    0.26
    ه
    0.26
    POSITIVE LOGITS
    ía
    0.29
    ată
    0.25
    ći
    0.25
    ăți
    0.25
    ally
    0.24
     that
    0.24
    ating
    0.24
    ada
    0.24
    ä
    0.23
    ielle
    0.23
    Activations Density 0.011%

    No Known Activations