© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52104
    Prev
    Next
    INDEX
    Explanations

    Dr. and comprehensive coverage

    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_31_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
    病
    0.91
     病
    0.90
     doença
    0.89
     disease
    0.89
     medical
    0.86
     pathology
    0.86
     المرض
    0.85
     bệnh
    0.82
     doenças
    0.82
     Disease
    0.81
    POSITIVE LOGITS
     fugitive
    0.39
    aré
    0.38
    敖
    0.37
     oon
    0.37
    Operations
    0.37
     افر
    0.37
     Executors
    0.37
    ంబేద్కర్
    0.36
     Rowing
    0.36
    Executor
    0.35
    Activations Density 0.024%

    No Known Activations