© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23604
    Prev
    Next
    INDEX
    Explanations

    religion and culture

    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_56_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
    riche
    0.38
    ऑन
    0.37
    ovington
    0.36
     alerg
    0.36
     Embedding
    0.36
    檢
    0.36
     sultry
    0.35
    leden
    0.35
     allergic
    0.34
    অতি
    0.34
    POSITIVE LOGITS
    挿
    0.43
     Thorough
    0.42
     து
    0.40
     thoroughly
    0.40
    とされる
    0.39
     cut
    0.38
    ipedia
    0.37
     Ster
    0.36
     Cut
    0.36
     Chow
    0.34
    Activations Density 0.002%

    No Known Activations