© 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. 208830
    Prev
    Next
    INDEX
    Explanations

    arithmetic expressions

    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
    努
    0.43
    ())
    0.40
     tại
    0.38
    ()))
    0.37
    enton
    0.37
     यू
    0.36
     ():
    0.36
    istungen
    0.36
     Blogging
    0.36
    靥
    0.36
    POSITIVE LOGITS
     coats
    0.52
     nitrates
    0.46
     ropa
    0.46
     coca
    0.44
     tax
    0.44
     pizza
    0.44
     scholarships
    0.44
     mineral
    0.43
     cuts
    0.42
     fibra
    0.42
    Activations Density 0.001%

    No Known Activations