© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 64089
    Prev
    Next
    INDEX
    Explanations

    colon

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     corr
    0.38
    adona
    0.38
     thirties
    0.37
     consiguió
    0.37
    訥
    0.35
     સા
    0.34
     보면은
    0.34
     tenían
    0.34
     ('
    0.33
     tenor
    0.33
    POSITIVE LOGITS
    l
    0.51
    1
    0.45
    lə
    0.42
    lw
    0.38
    9
    0.36
    Three
    0.36
    𝗹
    0.36
    lz
    0.35
    Archives
    0.34
    fæ
    0.34
    Activations Density 0.002%

    No Known Activations