© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52112
    Prev
    Next
    INDEX
    Explanations

    setCount or return

    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
     representan
    0.33
    きっかけ
    0.32
     reflexes
    0.30
     ফোনে
    0.29
     either
    0.29
     Representative
    0.29
     Vando
    0.29
    桐
    0.29
     साफ
    0.28
    cules
    0.28
    POSITIVE LOGITS
    BOL
    0.37
     herum
    0.32
    bol
    0.31
     रेट
    0.31
     heartache
    0.31
    няется
    0.31
    Cin
    0.30
     titers
    0.30
    ImageAlign
    0.30
     titer
    0.29
    Activations Density 0.004%

    No Known Activations