© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 87359
    Prev
    Next
    INDEX
    Explanations

    I

    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_60_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
     was
    0.40
     TCL
    0.40
     Teller
    0.34
    的标准
    0.34
     Ре
    0.34
     adm
    0.33
     '
    0.33
     am
    0.33
     Rep
    0.33
     appear
    0.33
    POSITIVE LOGITS
    the
    0.44
     the
    0.42
    kingen
    0.41
    ((-
    0.38
     cultivo
    0.37
     referring
    0.37
    (?
    0.35
     viendo
    0.35
    (
    0.35
    odik
    0.34
    Activations Density 0.000%

    No Known Activations