© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46457
    Prev
    Next
    INDEX
    Explanations

    religious titles and names

    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_13_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
    hatiti
    0.55
     ofthe
    0.54
    ке
    0.52
    که
    0.52
    тился
    0.52
    лению
    0.52
    ールの
    0.52
    嗪
    0.52
    ところに
    0.51
     wenigen
    0.50
    POSITIVE LOGITS
     p
    0.56
     could
    0.56
     hinder
    0.56
    ">
    0.55
    >
    0.55
     alliance
    0.54
     cause
    0.53
     handle
    0.53
     gol
    0.53
     life
    0.51
    Activations Density 0.000%

    No Known Activations