© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 206212
    Prev
    Next
    INDEX
    Explanations

    technical computer terms

    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_46_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
     Mo
    0.80
    Mo
    0.75
     mo
    0.64
    mo
    0.54
     M
    0.51
     F
    0.47
     مو
    0.47
     Mô
    0.47
     International
    0.47
     Fo
    0.45
    POSITIVE LOGITS
    ATEC
    0.39
    WP
    0.38
    ལ
    0.37
    William
    0.37
    LogProfile
    0.36
     WP
    0.36
    गिल
    0.36
    აშ
    0.36
     Caleb
    0.35
     भ्रमण
    0.35
    Activations Density 0.012%

    No Known Activations