© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91508
    Prev
    Next
    INDEX
    Explanations

    real-world consequences, deception

    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_3_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
    h
    1.02
    К
    0.80
    ور
    0.75
    م
    0.70
    м
    0.68
    р
    0.68
     cardinal
    0.67
     bygone
    0.67
     terminate
    0.65
     originating
    0.62
    POSITIVE LOGITS
    It
    0.75
    IT
    0.73
    ED
    0.71
    Configurations
    0.70
    ’
    0.68
    HK
    0.68
     It
    0.67
    あります
    0.67
    ۰
    0.66
     was
    0.66
    Activations Density 0.002%

    No Known Activations