© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31668
    Prev
    Next
    INDEX
    Explanations

    torch.nn module references

    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_40_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
    ╭
    0.40
    ────
    0.36
     رکھ
    0.36
    Happ
    0.36
    Barbara
    0.36
    glyphicon
    0.35
    िर
    0.35
     gruppi
    0.35
    🧍
    0.35
    happ
    0.34
    POSITIVE LOGITS
     inputRange
    0.39
    ntl
    0.36
     المنطقة
    0.36
     khu
    0.35
    区域
    0.35
     অঞ্চল
    0.34
     区
    0.34
     ფუნქ
    0.34
     CrossFit
    0.34
     функции
    0.33
    Activations Density 0.002%

    No Known Activations