© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40607
    Prev
    Next
    INDEX
    Explanations

    taunt

    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_3_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
    O
    0.76
     замети
    0.63
     examin
    0.61
    A
    0.61
    Q
    0.61
    ograp
    0.60
    ia
    0.59
    efore
    0.57
    ugh
    0.57
    uce
    0.57
    POSITIVE LOGITS
    ের
    0.85
    ς
    0.73
    s
    0.72
    দের
    0.72
     IDC
    0.66
    sports
    0.65
     FSH
    0.64
     saludar
    0.61
     BJP
    0.60
     DHS
    0.60
    Activations Density 0.000%

    No Known Activations