© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213374
    Prev
    Next
    INDEX
    Explanations

    Benadryl/Blizzard

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    W
    0.40
     Laud
    0.40
    Claud
    0.39
    Ｗ
    0.39
    IX
    0.39
    Ws
    0.38
    blockquote
    0.38
    ရော
    0.37
    SE
    0.37
    ఏ
    0.37
    POSITIVE LOGITS
     মন্দ
    0.41
     mcc
    0.40
    खिक
    0.39
    kül
    0.38
     tenths
    0.38
     naph
    0.38
     நிறை
    0.37
    गंध
    0.37
     냉
    0.37
    dct
    0.37
    Activations Density 0.000%

    No Known Activations