© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160300
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    re
    0.64
    data
    0.61
    icon
    0.60
    ו
    0.58
    id
    0.58
    yticks
    0.58
    ei
    0.57
    dic
    0.57
    و
    0.57
    eg
    0.57
    POSITIVE LOGITS
     силы
    0.54
     expressing
    0.51
     erect
    0.49
     للا
    0.49
     piuttosto
    0.48
     versed
    0.48
     करा
    0.48
    .”
    0.48
     sparen
    0.48
     shabby
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.