© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43480
    Prev
    Next
    INDEX
    Explanations

    "Attention is All You Need"

    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_22_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
     spitting
    0.44
    悰
    0.43
    妝
    0.41
    ىلى
    0.41
    rizioni
    0.41
    าส
    0.40
    शे
    0.40
    เพ
    0.40
     ஏதாவது
    0.40
     разобраться
    0.40
    POSITIVE LOGITS
    cca
    0.43
    hj
    0.42
     Tier
    0.42
     suggests
    0.41
     persists
    0.41
    ihl
    0.40
    :
    0.40
    hlen
    0.40
     revealed
    0.39
     saw
    0.39
    Activations Density 0.003%

    No Known Activations