© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6357
    Prev
    Next
    INDEX
    Explanations

    Indonesian research and elections

    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_40_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
    ANGMAR
    0.42
    ଲେ
    0.38
    엥
    0.38
    <0xB4>
    0.37
    hiqdev
    0.37
    añ
    0.37
    aimanapun
    0.36
    anday
    0.36
     այդ
    0.35
    玝
    0.35
    POSITIVE LOGITS
    ivation
    0.38
     types
    0.38
    образи
    0.37
     prost
    0.37
    suggest
    0.37
     Giac
    0.37
     vat
    0.36
     miller
    0.36
    types
    0.36
     enclosed
    0.35
    Activations Density 0.009%

    No Known Activations