© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198740
    Prev
    Next
    INDEX
    Explanations

    this / previous / leans

    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_12_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
    Burg
    0.36
    s
    0.36
    burg
    0.34
    Bound
    0.31
    齙
    0.31
    LAG
    0.30
    BUT
    0.30
    DAC
    0.30
    洍
    0.30
    CMR
    0.29
    POSITIVE LOGITS
    etailed
    0.37
     interferes
    0.36
     Pines
    0.36
     Гульнявыя
    0.36
     splashed
    0.34
     },
    0.34
     футболдук
    0.34
     Казіно
    0.34
    тием
    0.34
     வாங்க
    0.34
    Activations Density 0.001%

    No Known Activations