© 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. 214195
    Prev
    Next
    INDEX
    Explanations

    say "etics" or "etic"

    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
    Frank
    0.42
    FRANK
    0.39
     frank
    0.39
    frank
    0.39
    莊
    0.39
     frankly
    0.38
    ഗോ
    0.38
     Frankly
    0.38
    瑣
    0.38
     Lancaster
    0.37
    POSITIVE LOGITS
    لل
    0.42
     Corral
    0.41
     Hipp
    0.40
    දහ
    0.39
    allist
    0.38
     Rb
    0.37
    ビー
    0.37
     ото
    0.37
    rapy
    0.36
    대는
    0.36
    Activations Density 0.000%

    No Known Activations