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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245847
    Prev
    Next
    INDEX
    Explanations

    code explanations and improvements

    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_40_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
    uros
    0.39
     useCallback
    0.38
    Grace
    0.38
    Grade
    0.38
    Cep
    0.37
     grace
    0.36
    dbg
    0.36
    舘
    0.36
    Vs
    0.36
     dit
    0.35
    POSITIVE LOGITS
     modules
    0.54
     módulos
    0.50
     ph
    0.44
     Fet
    0.43
     module
    0.41
     broken
    0.40
     मॉड्यूल
    0.40
    modules
    0.40
    ()}")
    0.40
     butch
    0.40
    Activations Density 0.007%

    No Known Activations