© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43717
    Prev
    Next
    INDEX
    Explanations

    names followed by "Description"

    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_3_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
    ش
    0.67
    .",
    0.61
     thumbs
    0.60
    ,"
    0.54
    .</
    0.53
     trang
    0.53
    </h3>
    0.53
     visto
    0.53
     tive
    0.53
     hvordan
    0.53
    POSITIVE LOGITS
    s
    0.82
    ри
    0.76
    t
    0.71
    st
    0.68
    d
    0.67
    li
    0.65
    perfect
    0.64
    Assumption
    0.63
    gc
    0.63
    l
    0.62
    Activations Density 0.001%

    No Known Activations