© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 67025
    Prev
    Next
    INDEX
    Explanations

    React Router

    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
     influence
    0.39
     saffron
    0.39
    iamo
    0.37
     dinam
    0.37
    濰
    0.37
     third
    0.36
    Migration
    0.36
     तीसरा
    0.36
     action
    0.36
    Kind
    0.36
    POSITIVE LOGITS
    ឫ
    0.40
     runes
    0.39
     갑
    0.39
     Rune
    0.39
     Counseling
    0.38
    ELI
    0.38
     consequatur
    0.37
     تقری
    0.37
    YouTube
    0.37
    갑
    0.37
    Activations Density 0.000%

    No Known Activations