© 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. 132994
    Prev
    Next
    INDEX
    Explanations

    to be

    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
    кла
    0.38
    stackpath
    0.38
    តា
    0.37
    ⬅
    0.37
     कैंडिडेट
    0.35
    鲸
    0.35
    rova
    0.34
    XI
    0.34
     साहित्यिक
    0.34
     gale
    0.33
    POSITIVE LOGITS
     Be
    0.55
     be
    0.45
    Be
    0.44
    ifères
    0.42
    ToBe
    0.42
    족
    0.41
    be
    0.38
    ones
    0.38
    lices
    0.37
    zeros
    0.37
    Activations Density 0.000%

    No Known Activations