© 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. 218833
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas with variables

    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
    뚤
    0.41
     अर्ध
    0.40
    Correspond
    0.39
     బ్రిటి
    0.38
    corruption
    0.38
    YA
    0.37
     Coss
    0.37
    ባቸው
    0.36
     Dogs
    0.36
     desigualdad
    0.36
    POSITIVE LOGITS
     guard
    0.37
     pro
    0.36
    裤
    0.35
     buck
    0.34
     creates
    0.34
    uigen
    0.34
     commanding
    0.34
     scenery
    0.33
    友
    0.33
    ument
    0.33
    Activations Density 0.011%

    No Known Activations