© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 159309
    Prev
    Next
    INDEX
    Explanations

    errors and problems

    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_50_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
     giugno
    0.41
    ⓓ
    0.40
     moveable
    0.39
    ܒ
    0.39
    ⬆
    0.38
    ជ
    0.37
    clickView
    0.36
    🤡
    0.36
    愺
    0.36
     ottobre
    0.35
    POSITIVE LOGITS
     अस्वी
    0.36
     செய்யும்
    0.36
     matar
    0.36
    ्याचे
    0.36
    ‌
    0.36
     Tog
    0.35
     indiscriminate
    0.35
    Pad
    0.34
     ставить
    0.34
     ആണ്
    0.34
    Activations Density 0.078%

    No Known Activations