© 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. 237167
    Prev
    Next
    INDEX
    Explanations

    allow

    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
    Negative Logits
     কমাতে
    0.38
     verhind
    0.37
     restrict
    0.37
     restricting
    0.36
    blocking
    0.36
    minimize
    0.36
    amarin
    0.36
    귤
    0.36
    ใหญ
    0.35
    isel
    0.35
    POSITIVE LOGITS
     allow
    2.25
     allowing
    2.20
     Allowing
    2.13
     Allow
    2.09
    Allow
    2.08
    允许
    1.99
    allow
    1.97
    allowing
    1.97
     allows
    1.96
     позволя
    1.95
    Activations Density 0.132%

    No Known Activations