© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 146844
    Prev
    Next
    INDEX
    Explanations

    arithmetic operations or assignments

    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_18_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
    WithMessage
    0.35
    ง
    0.33
     बिना
    0.32
    )、
    0.32
    ErrorHandler
    0.31
    Settings
    0.31
    MainActivity
    0.31
    irken
    0.31
    =',
    0.30
    SuppressWarnings
    0.30
    POSITIVE LOGITS
     você
    0.37
     vocês
    0.37
     ustedes
    0.35
    yuan
    0.34
    roft
    0.34
    ção
    0.34
    yu
    0.32
     Y
    0.32
     yun
    0.32
    y
    0.32
    Activations Density 0.003%

    No Known Activations