© 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. 50563
    Prev
    Next
    INDEX
    Explanations

    wars, debt, Haitian

    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
     Agama
    0.44
    备案
    0.40
    囤
    0.35
    ευ
    0.35
     instructs
    0.34
     עצ
    0.34
     contend
    0.33
    uração
    0.33
     Igre
    0.32
    typeof
    0.32
    POSITIVE LOGITS
    肢
    0.39
    ମ୍
    0.37
     OPD
    0.37
    мы
    0.37
    ˙
    0.36
    モンド
    0.35
    ochastic
    0.35
    vit
    0.35
    orh
    0.35
     spokes
    0.34
    Activations Density 0.020%

    No Known Activations