© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62253
    Prev
    Next
    INDEX
    Explanations

    pricing

    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_11_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
    !"
    0.52
     brightly
    0.48
     chamado
    0.47
     finer
    0.46
    ب
    0.46
     caro
    0.46
    에
    0.46
    in
    0.44
     pot
    0.44
     hous
    0.43
    POSITIVE LOGITS
     Álvaro
    0.50
    دهم
    0.47
     झाल्यानंतर
    0.47
     MGM
    0.47
     ASM
    0.46
     Rupp
    0.46
    器
    0.46
     एप्पल
    0.45
     देंगे
    0.45
     Patty
    0.45
    Activations Density 0.000%

    No Known Activations