© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7528
    Prev
    Next
    INDEX
    Explanations

    turning heads or turning point

    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_39_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
    سبة
    0.39
    폐
    0.38
    hitung
    0.36
     Order
    0.36
    deleg
    0.35
    渇
    0.35
    ged
    0.35
    mes
    0.34
     obtenus
    0.34
    징
    0.34
    POSITIVE LOGITS
    Turning
    0.50
    Turn
    0.49
     turnips
    0.48
     turn
    0.47
     Turn
    0.47
     turnaround
    0.47
     turning
    0.47
     Turning
    0.47
     TURN
    0.43
     전환
    0.40
    Activations Density 0.011%

    No Known Activations