© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 141172
    Prev
    Next
    INDEX
    Explanations

    adversarial attacks

    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
     risky
    0.45
     N
    0.43
     risking
    0.43
     interpre
    0.38
    oreal
    0.38
     interpr
    0.38
     바뀌
    0.37
    baik
    0.37
     Baik
    0.37
     Reis
    0.37
    POSITIVE LOGITS
     Mani
    0.45
     эффектив
    0.43
     diathermy
    0.41
     효
    0.40
     ಇನ್ನೂ
    0.39
    пень
    0.39
    extension
    0.38
    ograd
    0.38
    manes
    0.37
    Золо
    0.37
    Activations Density 0.003%

    No Known Activations