© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16399
    Prev
    Next
    INDEX
    Explanations

    Lil

    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_15_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
    s
    0.51
    ز
    0.50
    뀐
    0.47
    ڑے
    0.47
    社長
    0.47
     presidente
    0.46
    '
    0.45
    r
    0.45
    ր
    0.45
    ्स
    0.45
    POSITIVE LOGITS
    vascular
    0.53
     muitas
    0.53
     Yadav
    0.52
     Pikachu
    0.52
     Banglades
    0.52
     Hezbollah
    0.52
     सूर्यकुमार
    0.52
     ചില
    0.51
     niektó
    0.51
     Citibank
    0.51
    Activations Density 0.002%

    No Known Activations