© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257904
    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_22_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
    ಂಗ್ರೆ
    0.50
    𝒃
    0.49
    imetro
    0.47
    बॉक्स
    0.46
    ަން
    0.46
     momentos
    0.46
    グラン
    0.46
    𝒙
    0.44
    カート
    0.44
    нак
    0.44
    POSITIVE LOGITS
     standings
    0.45
     Promotions
    0.44
     उत्तरप्रदेश
    0.42
    嶉
    0.42
     Experienced
    0.42
     duplicated
    0.42
     promotions
    0.41
     Specialties
    0.41
    ौज
    0.40
     Dieu
    0.40
    Activations Density 0.000%

    No Known Activations