© 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. 3726
    Prev
    Next
    INDEX
    Explanations

    engine, mid, opposed

    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
     cứng
    0.39
     Sink
    0.38
    sink
    0.37
    โก
    0.37
     सॉफ्टवेयर
    0.37
    Air
    0.36
    Fast
    0.36
    硬
    0.35
    擬
    0.35
    긱
    0.35
    POSITIVE LOGITS
     mid
    0.83
    mid
    0.65
     midrange
    0.58
     Mid
    0.57
     engine
    0.55
    মধ্য
    0.54
    Mid
    0.54
     midterm
    0.52
     MID
    0.52
    MID
    0.52
    Activations Density 0.018%

    No Known Activations