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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34911
    Prev
    Next
    INDEX
    Explanations

    text formats

    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_50_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
    …。
    0.40
     immense
    0.37
     […]
    0.35
    ventyConfig
    0.33
    parrot
    0.33
     perc
    0.33
     وسی
    0.33
     tony
    0.32
     societal
    0.32
    outines
    0.32
    POSITIVE LOGITS
     تَ
    0.42
    らかじめ
    0.38
    이버
    0.37
    不然
    0.37
    淐
    0.36
    OREM
    0.36
    udarstven
    0.34
     আচ্ছা
    0.34
     ARTICLE
    0.34
     আর্টিকেল
    0.34
    Activations Density 0.243%

    No Known Activations