© 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. 216365
    Prev
    Next
    INDEX
    Explanations

    percentages like 40% or 60%

    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
    ೯
    0.28
    ικο
    0.24
    ະພັນ
    0.24
    edinte
    0.23
     गर्म
    0.23
    çado
    0.23
     স্বর্ণ
    0.23
     Waist
    0.23
    vard
    0.23
    vyš
    0.22
    POSITIVE LOGITS
     comparative
    0.25
     aspects
    0.24
     fourth
    0.24
     ¹
    0.23
     cụ
    0.23
     disruptions
    0.23
    .¹
    0.23
     nacht
    0.23
     context
    0.22
    怎麼樣
    0.22
    Activations Density 0.001%

    No Known Activations