© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208940
    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_25_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
     africa
    0.45
    靴
    0.44
     아멘
    0.41
    ブック
    0.39
    Нор
    0.39
     Irlanda
    0.39
    芓
    0.39
    nonumber
    0.39
    挪
    0.39
    აგ
    0.39
    POSITIVE LOGITS
     или
    0.47
     hoặc
    0.44
     cùng
    0.40
     arba
    0.39
     isKindOfClass
    0.39
    \[
    0.39
    }{\
    0.39
    Semaphore
    0.38
     sufficient
    0.38
     capacity
    0.38
    Activations Density 0.000%

    No Known Activations