© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166479
    Prev
    Next
    INDEX
    Explanations

    phone numbers and emergency codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    射
    0.42
    issie
    0.41
    isfile
    0.38
    getImage
    0.38
     reflection
    0.37
    椰
    0.37
    reflection
    0.37
    スケ
    0.37
    reflect
    0.37
     getImage
    0.36
    POSITIVE LOGITS
    மிருந்து
    0.43
     Sol
    0.42
    ARM
    0.40
     функций
    0.39
     ব্যবসার
    0.39
     Translated
    0.38
    贓
    0.38
     Zav
    0.38
     ARM
    0.37
    чества
    0.37
    Activations Density 0.000%

    No Known Activations