© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134898
    Prev
    Next
    INDEX
    Explanations

    geographical region

    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_1_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
    ani
    1.38
    ao
    1.33
    uje
    1.17
    ou
    1.10
    ა
    1.04
    ים
    1.03
    ing
    1.02
    amina
    1.01
     an
    0.96
    ed
    0.95
    POSITIVE LOGITS
    س
    1.52
    ش
    1.15
    с
    1.07
    σ
    1.07
    一系列
    1.04
    ن
    1.02
    大的
    1.02
    S
    1.02
    L
    1.02
    یت
    1.00
    Activations Density 0.002%

    No Known Activations