© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17245
    Prev
    Next
    INDEX
    Explanations

    small items or clothing

    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_40_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
     smoothies
    0.38
     sandwiches
    0.35
     sandwich
    0.35
    padx
    0.35
    寬
    0.35
     cakes
    0.34
    mois
    0.34
     parfum
    0.34
    ストレ
    0.34
    ('$
    0.34
    POSITIVE LOGITS
    rekli
    0.45
    Directories
    0.45
     shopping
    0.41
     menus
    0.40
     folder
    0.40
     folders
    0.40
     Folder
    0.40
    Folder
    0.38
    folder
    0.38
    romagnet
    0.38
    Activations Density 0.070%

    No Known Activations