© 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. 133241
    Prev
    Next
    INDEX
    Explanations

    singin' in the rain

    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
     Dom
    0.49
     брю
    0.45
     dom
    0.43
     Bry
    0.43
    暴
    0.43
    Dom
    0.43
     Brut
    0.41
     vulnerable
    0.40
     Brent
    0.40
     Lyman
    0.38
    POSITIVE LOGITS
    anet
    0.41
    lanır
    0.39
    ayet
    0.39
     eponym
    0.37
    egos
    0.37
    ানী
    0.37
     mối
    0.37
    FName
    0.37
    瞇
    0.37
    皇后
    0.36
    Activations Density 0.000%

    No Known Activations