© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44665
    Prev
    Next
    INDEX
    Explanations

    chess openings, state abbreviations

    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_13_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
    Lincoln
    0.47
     Shat
    0.46
     Putra
    0.46
     Measurement
    0.46
    প
    0.46
     Retired
    0.46
     количе
    0.46
     Seneca
    0.46
    紂
    0.46
     Lincoln
    0.45
    POSITIVE LOGITS
    elser
    0.49
    leurs
    0.46
    ळख
    0.45
     profiter
    0.44
     realms
    0.44
    和服务
    0.43
    ALOG
    0.43
     avances
    0.43
    🅰
    0.43
     حل
    0.43
    Activations Density 0.000%

    No Known Activations