© 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. 218481
    Prev
    Next
    INDEX
    Explanations

    education and career paths

    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
     semasa
    0.47
    LuaPush
    0.45
    ছার
    0.40
     vremena
    0.39
    糉
    0.39
     электрон
    0.39
    iswa
    0.39
     motionProxy
    0.39
     striis
    0.38
    恫
    0.38
    POSITIVE LOGITS
    widgets
    0.39
    æs
    0.38
    movied
    0.37
     induced
    0.35
    io
    0.35
     integr
    0.35
     aspir
    0.35
    inductive
    0.35
     indulgence
    0.35
    ats
    0.34
    Activations Density 0.001%

    No Known Activations