© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218495
    Prev
    Next
    INDEX
    Explanations

    language and mathematical simplification

    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
    াজন
    0.41
     AW
    0.37
     colours
    0.36
    पीसी
    0.36
    Renk
    0.36
     Leia
    0.35
     colori
    0.35
    ":[{"
    0.35
    ायी
    0.35
    Compl
    0.34
    POSITIVE LOGITS
    ócio
    0.40
     paycheck
    0.38
    товано
    0.38
     Commerce
    0.37
     stringWith
    0.37
     potřeb
    0.36
     genealog
    0.36
     Textbook
    0.36
     ક્
    0.36
    arete
    0.36
    Activations Density 0.000%

    No Known Activations