© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1297
    Prev
    Next
    INDEX
    Explanations

    1-800-656-HOPE

    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
    Prem
    0.32
    waste
    0.31
     Prem
    0.30
     déchets
    0.29
    Waste
    0.29
     Toni
    0.28
    ༺
    0.28
    Dak
    0.27
    వే
    0.27
     القاعدة
    0.27
    POSITIVE LOGITS
     GV
    0.28
     Restaurant
    0.27
    bv
    0.27
    ബ്‌
    0.27
     ملین
    0.26
    °)
    0.25
    metall
    0.25
    ментов
    0.25
     Smoothing
    0.25
    ರಿಂದ
    0.25
    Activations Density 0.010%

    No Known Activations