© 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. 92099
    Prev
    Next
    INDEX
    Explanations

    dozen followed by a noun

    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
    ode
    0.68
     infek
    0.67
     construe
    0.67
    pence
    0.64
    donut
    0.63
     crebre
    0.62
    <unused1799>
    0.61
    পুণ
    0.60
     softens
    0.59
    dancer
    0.59
    POSITIVE LOGITS
    是
    0.76
    一
    0.75
    ص
    0.73
    य
    0.70
    ب
    0.67
    可以
    0.63
    那些
    0.59
    з
    0.58
    ল
    0.58
    غ
    0.57
    Activations Density 0.000%

    No Known Activations