© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 467
    Prev
    Next
    INDEX
    Explanations

    E followed by letters or numbers

    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_38_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
    !==
    0.40
    zuoye
    0.40
     diamante
    0.39
    andae
    0.38
     flattered
    0.37
     親
    0.37
     tuo
    0.37
     लाज
    0.37
     Defaults
    0.37
    ixeira
    0.36
    POSITIVE LOGITS
     E
    0.66
    E
    0.55
     EJ
    0.54
     ED
    0.52
     EH
    0.52
     Е
    0.52
     EAC
    0.51
     ES
    0.50
     EG
    0.50
     ECL
    0.50
    Activations Density 0.124%

    No Known Activations