© 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. 202442
    Prev
    Next
    INDEX
    Explanations

    until

    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
     этого
    0.41
    DOWN
    0.41
    alá
    0.38
    르고
    0.37
    umphed
    0.37
    ➁
    0.37
    сий
    0.36
     भे
    0.36
     persuade
    0.35
    ících
    0.35
    POSITIVE LOGITS
     beside
    0.37
     Concurrent
    0.37
    tr
    0.36
     kt
    0.36
     Kn
    0.36
     Efficient
    0.36
     Adjacent
    0.35
     ${\
    0.35
     ریا
    0.35
     Beside
    0.35
    Activations Density 0.001%

    No Known Activations