© 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. 127316
    Prev
    Next
    INDEX
    Explanations

    boric acid and springs

    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
    וני
    0.66
    cale
    0.60
    '
    0.60
    cube
    0.57
    asc
    0.55
    cak
    0.54
     দাও
    0.53
    וט
    0.53
    納税
    0.53
     ostatnich
    0.53
    POSITIVE LOGITS
    ל
    0.72
    其他
    0.70
     matéria
    0.64
    టర్‌
    0.64
    л
    0.63
    тировать
    0.62
    ти
    0.61
    те
    0.61
    ло
    0.60
     );
    0.60
    Activations Density 0.000%

    No Known Activations