© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215766
    Prev
    Next
    INDEX
    Explanations

    balancing itinerary elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     θερ
    0.46
     beschik
    0.43
     डिप्लोमा
    0.40
    ☎
    0.40
     পিক
    0.39
    Aprend
    0.39
    ocular
    0.38
     PERSONAL
    0.38
    Diploma
    0.38
    Photography
    0.38
    POSITIVE LOGITS
     prefabricated
    0.42
     Contributors
    0.41
     mutilated
    0.38
    팡
    0.37
     famous
    0.36
     nonparametric
    0.36
     Mahogany
    0.35
    old
    0.35
     successfully
    0.35
     twisted
    0.35
    Activations Density 0.007%

    No Known Activations