© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60056
    Prev
    Next
    INDEX
    Explanations

    each one

    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_11_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
     every
    0.80
     každ
    0.80
     每个
    0.79
    每
    0.79
     mỗi
    0.76
     each
    0.76
    每個
    0.75
     setiap
    0.75
     každý
    0.72
    every
    0.71
    POSITIVE LOGITS
    सीएस
    0.81
    ेड
    0.76
    िंग
    0.71
    टीएम
    0.68
    ić
    0.68
    ாக
    0.66
    ی
    0.64
    ing
    0.63
    jų
    0.63
    ۔
    0.63
    Activations Density 0.021%

    No Known Activations