© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29804
    Prev
    Next
    INDEX
    Explanations

    security settings

    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
    ドライ
    0.37
    ポルト
    0.36
    idefinite
    0.35
    printf
    0.35
     실
    0.35
    uaries
    0.35
     bounding
    0.34
     sdl
    0.34
    භ
    0.34
    0.34
    POSITIVE LOGITS
    이면
    0.44
     postponed
    0.39
     post
    0.39
     लंबे
    0.39
     Wahr
    0.39
     tools
    0.36
    asted
    0.36
     Шта
    0.36
     ৪৯
    0.36
    फेर
    0.36
    Activations Density 0.016%

    No Known Activations