© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196945
    Prev
    Next
    INDEX
    Explanations

    advocate or Devil's advocate

    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_46_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
    aporation
    0.40
     radiolysis
    0.39
    椇
    0.39
    เล่น
    0.38
    ждён
    0.38
     সুইড
    0.38
    odesmium
    0.37
    ithmetic
    0.37
    <0xDD>
    0.37
     মুজিবের
    0.37
    POSITIVE LOGITS
    Adv
    1.73
     adv
    1.65
     advocate
    1.65
     Advocate
    1.62
     advocates
    1.57
    adv
    1.56
     Advocates
    1.55
     advoc
    1.52
     Adv
    1.50
     advocacy
    1.44
    Activations Density 0.000%

    No Known Activations