© 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. 236571
    Prev
    Next
    INDEX
    Explanations

    Holy code

    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
    గొ
    0.39
    Լ
    0.39
    ስታ
    0.38
    いただける
    0.38
     salut
    0.36
    범
    0.36
    ழு
    0.36
    薰
    0.36
    ಲ್ಯ
    0.35
     guarding
    0.35
    POSITIVE LOGITS
     Holy
    0.53
    holy
    0.53
     holy
    0.53
     kode
    0.51
    Kod
    0.50
    Holy
    0.50
    kode
    0.49
    CODE
    0.48
     Kode
    0.48
     code
    0.48
    Activations Density 0.002%

    No Known Activations