© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 66299
    Prev
    Next
    INDEX
    Explanations

    I

    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_46_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
     pumpkin
    0.39
     очень
    0.38
     descu
    0.38
    pumpkin
    0.37
     pumpkins
    0.37
     ιδια
    0.37
    onaise
    0.36
    ᆻ
    0.36
     Pumpkin
    0.36
    മാക്കി
    0.36
    POSITIVE LOGITS
    HB
    0.39
     Arr
    0.39
    祥
    0.39
     arranging
    0.38
    HJ
    0.38
     complementarity
    0.38
     EMPTY
    0.38
     OM
    0.37
     Fad
    0.37
     ओम
    0.37
    Activations Density 0.003%

    No Known Activations