© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209551
    Prev
    Next
    INDEX
    Explanations

    unlucky

    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_5_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
    1.15
    
    1.02
    h
    0.98
    stride
    0.86
    subcategory
    0.81
    ranging
    0.80
    ास
    0.79
    though
    0.79
    sobre
    0.79
    ahankan
    0.79
    POSITIVE LOGITS
    ت
    1.83
    ED
    1.64
    V
    1.55
    ن
    1.53
    C
    1.52
    X
    1.51
    IT
    1.44
    H
    1.44
    R
    1.43
    G
    1.43
    Activations Density 0.000%

    No Known Activations