© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174500
    Prev
    Next
    INDEX
    Explanations

    `eval` and `await` usage

    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_20_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
    ChangeEvent
    0.21
    ⟣
    0.20
     Mutation
    0.19
    Whether
    0.19
     согла
    0.19
    和
    0.19
    Mutation
    0.18
    変
    0.18
     INSTIT
    0.18
     वेजिट
    0.18
    POSITIVE LOGITS
    l
    0.19
     pues
    0.18
     coder
    0.18
    coder
    0.18
     mức
    0.18
    ATIVES
    0.18
     eléctrica
    0.17
    pkl
    0.17
     équipements
    0.17
     welder
    0.17
    Activations Density 0.001%

    No Known Activations