© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 62896
    Prev
    Next
    INDEX
    Explanations

    endogenous or endothelium

    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_41_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
     nucleic
    1.23
     Nucleic
    1.21
    Nucle
    0.80
     Nucl
    0.79
    核
    0.70
    nucle
    0.66
     nuclé
    0.65
     nuk
    0.64
     누
    0.64
     핵
    0.63
    POSITIVE LOGITS
     endot
    1.31
     End
    0.90
    エンド
    0.75
     py
    0.73
    End
    0.73
     Endo
    0.72
     END
    0.68
    end
    0.63
     endothelial
    0.63
     endothelium
    0.63
    Activations Density 0.013%

    No Known Activations