© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 209005
    Prev
    Next
    INDEX
    Explanations

    a

    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_56_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
    *{
    0.36
     accumulator
    0.35
    تع
    0.35
    بال
    0.34
    사람
    0.34
    लर
    0.33
    ראש
    0.33
    )}^
    0.33
    യിലും
    0.33
    .$,
    0.32
    POSITIVE LOGITS
     Considering
    0.37
     sevent
    0.36
     seguintes
    0.35
     Recognizing
    0.35
    ems
    0.35
     Rxc
    0.35
    istos
    0.35
     Tick
    0.35
    istics
    0.34
     Three
    0.34
    Activations Density 0.001%

    No Known Activations