© 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. 76957
    Prev
    Next
    INDEX
    Explanations

    **Important Note:**

    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
     What
    0.45
    ：
    0.42
     Registered
    0.41
    :.
    0.40
    :
    0.39
    ://
    0.39
    :*
    0.39
     heap
    0.39
    What
    0.38
     Writing
    0.38
    POSITIVE LOGITS
     लहर
    0.37
     وړاندوینې
    0.35
    FundMe
    0.35
    ẩn
    0.35
     выпусти
    0.35
    ដៃ
    0.34
    वाइड
    0.34
    ចំនួន
    0.33
    ු
    0.33
     করিয়াছি
    0.33
    Activations Density 0.002%

    No Known Activations