© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 60549
    Prev
    Next
    INDEX
    Explanations

    Facebook

    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_59_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
     Take
    0.43
    اتھ
    0.38
     Email
    0.38
    Take
    0.37
     Whatsapp
    0.37
    ethoscope
    0.37
    K
    0.37
     fb
    0.37
    MBC
    0.36
    alors
    0.36
    POSITIVE LOGITS
    sendPluginResult
    0.40
     său
    0.38
     就
    0.38
     실
    0.38
     му
    0.37
     않고
    0.37
     హె
    0.36
     ポ
    0.36
     Север
    0.36
     ハン
    0.36
    Activations Density 0.001%

    No Known Activations