© 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. 215587
    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
     memória
    0.40
    pack
    0.40
    жей
    0.38
    逃
    0.37
     kare
    0.37
    曬
    0.36
     රා
    0.36
     秋冬
    0.36
     너무
    0.35
    took
    0.35
    POSITIVE LOGITS
    指向
    0.38
    尣
    0.38
    linearity
    0.38
    เชื้อ
    0.37
     Magazine
    0.37
     epsilon
    0.37
    溌
    0.37
     unsubstituted
    0.37
    UCLEAR
    0.36
    すすめ
    0.35
    Activations Density 0.000%

    No Known Activations