© 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. 69331
    Prev
    Next
    INDEX
    Explanations

    Software development terms

    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
     V
    0.66
    V
    0.62
     Vanderbilt
    0.48
     ভ
    0.46
     Vantage
    0.45
    Vu
    0.44
     Vand
    0.43
    VU
    0.42
    VD
    0.42
    Kel
    0.42
    POSITIVE LOGITS
     Carriers
    0.43
     Carrier
    0.39
     ಆಗ
    0.37
    дентифика
    0.37
     manzanas
    0.37
     Logical
    0.36
     ચ
    0.36
     Italia
    0.36
     логи
    0.36
     ইলেক
    0.35
    Activations Density 0.047%

    No Known Activations