© 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. 41819
    Prev
    Next
    INDEX
    Explanations

    stroke attribute

    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_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
     racquet
    0.43
     fero
    0.43
    sels
    0.42
     벌
    0.41
     pály
    0.41
     불구
    0.41
     lycée
    0.41
    }^{+\
    0.40
     tilbage
    0.40
    professional
    0.40
    POSITIVE LOGITS
    வின்
    0.48
     cleanliness
    0.46
    Clean
    0.46
    Stream
    0.45
    Surface
    0.45
    سط
    0.44
    Deep
    0.44
     Cleaning
    0.43
    Cleaning
    0.43
     Uns
    0.42
    Activations Density 0.001%

    No Known Activations