© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91934
    Prev
    Next
    INDEX
    Explanations

    `[Flags]` enum or BindingFlags

    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
    s
    0.58
    ையான
    0.54
    ים
    0.54
    मी
    0.50
    '!
    0.49
     Microwave
    0.49
    '?
    0.49
    वर्ग
    0.47
     County
    0.47
    <0xB1>
    0.47
    POSITIVE LOGITS
    addKill
    0.51
    ⣀
    0.51
    炲
    0.50
     kunnen
    0.49
    čk
    0.49
    ściej
    0.48
    گرد
    0.48
    un
    0.47
     cactus
    0.47
    beatCounter
    0.47
    Activations Density 0.001%

    No Known Activations