© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166154
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    根据
    0.42
     troll
    0.38
     Concentrate
    0.38
    根據
    0.37
     Lighthouse
    0.36
    क्रमण
    0.36
    anonymous
    0.36
    얽
    0.35
     exhibitors
    0.35
    wu
    0.35
    POSITIVE LOGITS
    枌
    0.41
    اعری
    0.39
     વડે
    0.37
    字体
    0.36
     rit
    0.35
    玫
    0.35
    ܡ
    0.35
    Primitive
    0.35
    篩
    0.35
    垡
    0.35
    Activations Density 0.000%

    No Known Activations