© 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. 237033
    Prev
    Next
    INDEX
    Explanations

    to

    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
    bae
    0.39
    萑
    0.39
    ETE
    0.39
     cut
    0.38
    טר
    0.38
     партії
    0.38
     Pest
    0.37
     வே
    0.37
    ស្ស
    0.36
    قطع
    0.36
    POSITIVE LOGITS
     complimentary
    0.45
     complementary
    0.43
    轿
    0.41
     compl
    0.40
     compliance
    0.39
    зд
    0.39
     Complement
    0.39
    いを
    0.39
     complement
    0.39
     compliment
    0.39
    Activations Density 0.000%

    No Known Activations