© 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. 226754
    Prev
    Next
    INDEX
    Explanations

    gregorian calendar dates

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ad
    1.18
     in
    1.15
    ant
    1.15
    ও
    1.11
    ine
    1.07
    ill
    1.05
    op
    1.03
    ed
    1.00
    pt
    0.98
    it
    0.97
    POSITIVE LOGITS
    WITH
    0.93
     Při
    0.89
     Foi
    0.88
     Hesap
    0.88
     Moż
    0.88
     Jezus
    0.86
    の影響
    0.84
    用
    0.84
     Před
    0.84
    TGFuZ
    0.84
    Activations Density 0.002%

    No Known Activations