© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48824
    Prev
    Next
    INDEX
    Explanations

    a followed by a generic descriptor

    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_10_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
     \
    0.53
    F
    0.52
     فيلم
    0.48
    D
    0.47
     Signific
    0.46
    W
    0.45
    P
    0.45
     agosto
    0.44
    ंजे
    0.44
     I
    0.43
    POSITIVE LOGITS
    да
    0.58
    ↵
    0.57
    αν
    0.52
    даги
    0.51
    t
    0.45
    ات
    0.44
    дан
    0.44
    ան
    0.44
    даг
    0.44
    ор
    0.43
    Activations Density 0.090%

    No Known Activations