© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210593
    Prev
    Next
    INDEX
    Explanations

    sequence of words

    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_20_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
    勛
    0.27
    Hallo
    0.25
    Via
    0.25
     حول
    0.24
    ሉ
    0.24
    ุ่น
    0.24
    פל
    0.24
    Pass
    0.24
     farlo
    0.24
    輸
    0.24
    POSITIVE LOGITS
     Име
    0.31
    czech
    0.29
    ීය
    0.27
     choreographer
    0.27
     Incidentally
    0.27
     पृथ
    0.26
     Пет
    0.26
     Communic
    0.26
     Wearing
    0.25
     призна
    0.25
    Activations Density 0.002%

    No Known Activations