© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201741
    Prev
    Next
    INDEX
    Explanations

    Dutch, East, South, Han, Hall

    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_12_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
     offen
    0.10
     saan
    0.10
    ク
    0.10
     Nm
    0.09
     যেকোন
    0.09
    เยอะ
    0.09
     =
    0.09
    攻击
    0.09
    ра
    0.09
     Aaron
    0.09
    POSITIVE LOGITS
    मिया
    0.10
    ópolis
    0.09
    ких
    0.09
     Hask
    0.09
     Mét
    0.09
    密封
    0.09
    illis
    0.09
    στε
    0.09
    ప్తి
    0.09
    ہار
    0.09
    Activations Density 0.001%

    No Known Activations