© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208406
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations

    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_20_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
    砳
    0.44
    uları
    0.42
     কাজ
    0.41
    util
    0.40
    ucaly
    0.40
    <unused58>
    0.39
     کاربر
    0.39
     zelfs
    0.38
     kih
    0.38
     myriad
    0.38
    POSITIVE LOGITS
     S
    0.42
     fudge
    0.41
     Rom
    0.41
     Romeo
    0.41
     es
    0.40
     I
    0.40
     Sigma
    0.40
     seasoning
    0.39
    чество
    0.39
    Sigma
    0.39
    Activations Density 0.000%

    No Known Activations