© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142124
    Prev
    Next
    INDEX
    Explanations

    inpainting

    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_12_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
     ingen
    0.62
     o
    0.51
     tema
    0.51
    '
    0.51
     آنها
    0.50
     Ingen
    0.50
    ľad
    0.50
     препарат
    0.50
     $(<
    0.50
    lem
    0.50
    POSITIVE LOGITS
    UIActions
    0.54
     فوټبال
    0.54
    AppBsky
    0.52
    Expenses
    0.48
     зав
    0.48
     shri
    0.48
    SRS
    0.47
    ECK
    0.47
    Paid
    0.47
    Finished
    0.47
    Activations Density 0.002%

    No Known Activations