© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173241
    Prev
    Next
    INDEX
    Explanations

    math operations like division and multiplication

    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
     approve
    0.36
     Approve
    0.31
     isomorphism
    0.31
     Objective
    0.30
    }^{+
    0.29
    ,(
    0.29
    。（
    0.28
    ',['
    0.28
     posit
    0.28
     timeout
    0.28
    POSITIVE LOGITS
    gespr
    0.33
     cashless
    0.30
     Divider
    0.30
    വ്യ
    0.30
    Fala
    0.30
    steen
    0.30
    SPIR
    0.30
     डिवाइड
    0.30
     دینے
    0.30
    بعض
    0.30
    Activations Density 0.008%

    No Known Activations