© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45714
    Prev
    Next
    INDEX
    Explanations

    think

    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_13_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
     voire
    0.46
     來
    0.46
    ruits
    0.46
     bactéri
    0.45
    Array
    0.44
     antibacterial
    0.43
    ガイ
    0.43
     KAHN
    0.43
    プレイヤー
    0.43
    ؟
    0.43
    POSITIVE LOGITS
    s
    0.54
    isy
    0.52
    íf
    0.47
    ip
    0.46
    ata
    0.46
    sembles
    0.45
    ies
    0.44
     recepción
    0.44
    鿆
    0.43
    atol
    0.43
    Activations Density 0.003%

    No Known Activations