© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 151986
    Prev
    Next
    INDEX
    Explanations

    specific technical items and jargon

    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_23_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
     occasionally
    0.54
    StatusCodes
    0.50
     dave
    0.45
     अमित
    0.45
    絠
    0.44
     ancestor
    0.44
    ÈRES
    0.43
     moſt
    0.43
     Occasionally
    0.43
     представлены
    0.43
    POSITIVE LOGITS
     沒有
    0.46
     没有
    0.43
    órmula
    0.43
    ᱴ
    0.42
    ｒ
    0.39
    Uploading
    0.38
     不同
    0.38
    ছোট
    0.38
    asp
    0.38
    特定的
    0.38
    Activations Density 0.000%

    No Known Activations