© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137367
    Prev
    Next
    INDEX
    Explanations

    transcripts

    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_46_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
     volum
    0.41
    敀
    0.41
    氇
    0.40
    敔
    0.39
     BU
    0.38
     agres
    0.38
     conservatively
    0.37
     cha
    0.36
     results
    0.35
     చ
    0.35
    POSITIVE LOGITS
     पेशकश
    0.38
    편집
    0.38
     मक्
    0.38
    สะ
    0.37
    aconit
    0.37
    йти
    0.37
    кия
    0.36
    apprentissage
    0.36
    ORDERS
    0.36
     Tart
    0.36
    Activations Density 0.002%

    No Known Activations