© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32885
    Prev
    Next
    INDEX
    Explanations

    division 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_31_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
     presenters
    0.38
     coffees
    0.37
    ष्ठी
    0.37
    铭
    0.37
     क्रांतिकार
    0.37
    зня
    0.36
     जैसी
    0.36
     расстоя
    0.36
    वर्
    0.35
     引き
    0.35
    POSITIVE LOGITS
     Kush
    0.45
     turnover
    0.39
     utt
    0.38
     UTC
    0.38
    Comprehensive
    0.38
    Indigo
    0.38
     luch
    0.37
    羟
    0.37
     Oxford
    0.37
    Summit
    0.37
    Activations Density 0.005%

    No Known Activations