© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14145
    Prev
    Next
    INDEX
    Explanations

    multiplication operations

    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_40_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
     milliers
    0.32
     nameWithOwner
    0.32
    諾
    0.30
    mäßige
    0.30
     тысяч
    0.30
    dele
    0.30
    种类
    0.29
    Feet
    0.29
    odată
    0.29
    ∴
    0.29
    POSITIVE LOGITS
     Tink
    0.33
     Ants
    0.32
     ontological
    0.30
     Ting
    0.30
     parting
    0.29
     Fleming
    0.28
     infant
    0.28
     וכ
    0.28
     Tint
    0.27
    ตาย
    0.27
    Activations Density 0.012%

    No Known Activations