© 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. 90922
    Prev
    Next
    INDEX
    Explanations

    back together

    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
    at
    0.83
    ↵
    0.82
     backdoor
    0.82
     backend
    0.69
    he
    0.68
    well
    0.67
    ur
    0.65
     Backend
    0.65
    로
    0.65
    ل
    0.64
    POSITIVE LOGITS
    ق
    0.75
    㡴
    0.75
     traer
    0.74
    Ｕ
    0.71
     tedesco
    0.70
    
    0.70
    الإ
    0.70
    h
    0.68
    ется
    0.67
     pelea
    0.67
    Activations Density 0.002%

    No Known Activations