© 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. 34207
    Prev
    Next
    INDEX
    Explanations

    table rows and headers

    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
    ត្
    0.51
    ocytosis
    0.46
     الاساس
    0.44
    attice
    0.40
    lasma
    0.39
    opsis
    0.39
     enquire
    0.38
    
    0.38
    opend
    0.37
    odos
    0.36
    POSITIVE LOGITS
     Sarmiento
    0.40
     gosh
    0.39
     beautiful
    0.38
    нам
    0.37
     kli
    0.36
     authoritative
    0.36
     tools
    0.36
    配套
    0.35
     burial
    0.35
     hoa
    0.35
    Activations Density 0.002%

    No Known Activations