© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48948
    Prev
    Next
    INDEX
    Explanations

    percentages or proportion of population

    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
    公園
    0.46
    STATIC
    0.41
    𒅅
    0.41
     organismes
    0.40
    ottak
    0.39
    savefig
    0.39
     ہوسکتا
    0.39
    伍章
    0.39
    ĕç
    0.38
     percents
    0.38
    POSITIVE LOGITS
     Day
    0.42
     Lat
    0.42
     Hol
    0.41
     Bang
    0.40
     Geographic
    0.40
     Prof
    0.40
     Tetrahedron
    0.38
     D
    0.38
     Jordan
    0.38
     Ao
    0.38
    Activations Density 0.001%

    No Known Activations