© 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. 148942
    Prev
    Next
    INDEX
    Explanations

    K

    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
    htu
    0.46
    brauch
    0.40
    ুকু
    0.40
    厮
    0.40
    otroph
    0.39
    恶
    0.39
    erical
    0.39
    illar
    0.39
    altung
    0.39
    an
    0.38
    POSITIVE LOGITS
     Kerala
    0.46
     kerala
    0.46
     Bhutan
    0.46
     Minnesota
    0.45
     Tibet
    0.44
     Indien
    0.43
    :<
    0.42
     Malayalam
    0.41
    :',
    0.41
     인도
    0.41
    Activations Density 0.000%

    No Known Activations