© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199696
    Prev
    Next
    INDEX
    Explanations

    baby carrier

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Од
    0.41
     Wyoming
    0.40
     الأد
    0.39
     BUTTON
    0.38
     የማ
    0.38
     Romney
    0.38
    ="//
    0.38
    BROOK
    0.37
    歉
    0.37
     Cy
    0.37
    POSITIVE LOGITS
     MCSF
    0.39
    kel
    0.39
     फैली
    0.39
     kel
    0.38
    M
    0.38
    ഒ
    0.38
     moles
    0.38
    趋
    0.37
     cloned
    0.37
    lni
    0.37
    Activations Density 0.000%

    No Known Activations