© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18834
    Prev
    Next
    INDEX
    Explanations

    conditions that qualify

    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_34_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     indors
    0.40
    neut
    0.38
    훤
    0.37
     problemlos
    0.37
    纂
    0.37
    พน
    0.36
     преду
    0.35
     సామ
    0.35
    $%
    0.35
     выбирать
    0.35
    POSITIVE LOGITS
     qualifies
    0.74
     threshold
    0.71
    Threshold
    0.68
     qualify
    0.66
     qualifying
    0.66
     thresholds
    0.66
     Threshold
    0.64
     constitutes
    0.63
     classifies
    0.63
     classified
    0.61
    Activations Density 0.171%

    No Known Activations