© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134348
    Prev
    Next
    INDEX
    Explanations

    rich in history and culture

    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_37_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
     extreme
    0.43
    extreme
    0.41
    uhe
    0.38
     ದಿ
    0.38
    極
    0.37
     Extreme
    0.37
    Extreme
    0.36
     Daftar
    0.34
     Slightly
    0.34
    termination
    0.34
    POSITIVE LOGITS
    不见
    0.44
    aches
    0.38
    Lord
    0.37
    间
    0.37
    أن
    0.36
     ot
    0.36
    INGS
    0.36
     heen
    0.36
    鍋
    0.36
    锅
    0.36
    Activations Density 0.005%

    No Known Activations