© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2461
    Prev
    Next
    INDEX
    Explanations

    local control and states

    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_40_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
    classification
    0.41
    PROCESS
    0.41
     Stage
    0.40
     outFile
    0.37
    ণের
    0.37
    ecycle
    0.35
    myLabels
    0.35
     Apo
    0.35
    ミ
    0.35
     سہ
    0.35
    POSITIVE LOGITS
     local
    0.91
     locally
    0.85
    local
    0.84
    本地
    0.77
    Local
    0.73
    locally
    0.71
     Locally
    0.68
     LOCAL
    0.67
     स्थानीय
    0.67
     lokal
    0.67
    Activations Density 0.020%

    No Known Activations