© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8736
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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_13_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
     und
    0.32
    the
    0.31
     (
    0.30
     e
    0.30
     not
    0.30
     p
    0.29
     l
    0.29
     the
    0.29
     en
    0.29
          
    0.28
    POSITIVE LOGITS
    𒈬
    0.31
    福祉
    0.29
     ಎಷ್ಟು
    0.29
    ARMA
    0.28
    ága
    0.27
     Австра
    0.27
    hatiti
    0.27
     స్థితి
    0.27
     diarias
    0.27
     Нью
    0.27
    Activations Density 0.030%

    No Known Activations