© 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. 63570
    Prev
    Next
    INDEX
    Explanations

    product qualities

    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
     शीर्षक
    0.46
     ಮಾಹಿತ
    0.46
    繹
    0.41
    เภท
    0.41
     schwier
    0.39
     razvoj
    0.39
    情報の
    0.37
    ષા
    0.36
    맟
    0.36
     जानकारी
    0.35
    POSITIVE LOGITS
     than
    0.73
    than
    0.68
     Than
    0.61
    Than
    0.60
    Appearance
    0.59
    Does
    0.59
     does
    0.58
    does
    0.55
     Does
    0.55
     decât
    0.54
    Activations Density 0.001%

    No Known Activations