© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44588
    Prev
    Next
    INDEX
    Explanations

    The explanation should be based on identifying a common theme or pattern in the MAX_ACTIVATING_TOKENS and TOP_ACTIVATING_TEXTS.Looking at MAX_ACTIVATING_TOKENS:- bombs- bomb- bomb- bomb- MP- en (part of EMP)- DE (part of HEMP)- ant (part of Hambantota?)- derivedLooking at TOP_ACTIVATING_TEXTS:- "high-altitude EMP (HEMP)"- "hydrogen bomb"- "hydrogen bomb" (again)- "Mark 17 hydrogen bomb"- "Hambantota Port"- "hemp-derived cannabinoid products"EMP, bomb, derive

    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
    ok
    0.83
    ри
    0.78
    ilot
    0.73
    تس
    0.73
    થી
    0.71
    atas
    0.70
    rī
    0.69
    restrial
    0.69
    authored
    0.68
    お願いします
    0.68
    POSITIVE LOGITS
    ו
    0.88
     be
    0.76
    ，
    0.75
     filme
    0.73
    ↵
    0.71
    و
    0.68
    ก
    0.68
    м
    0.67
    </h3>
    0.66
    ма
    0.66
    Activations Density 0.000%

    No Known Activations