© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62424
    Prev
    Next
    INDEX
    Explanations

    features and cons

    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_59_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
     If
    0.47
     ܗ
    0.40
     taint
    0.40
             
    0.38
     tüm
    0.38
    orsion
    0.37
     ኢ
    0.37
     merda
    0.37
     ഈ
    0.37
     Dacă
    0.37
    POSITIVE LOGITS
    며
    0.54
    .•
    0.49
    ."-
    0.48
    。"
    0.48
    하며
    0.47
     but
    0.46
     Luxurious
    0.46
    리와
    0.46
    .";
    0.46
     (|
    0.45
    Activations Density 0.022%

    No Known Activations