© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172353
    Prev
    Next
    INDEX
    Explanations

    formation

    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
    那边
    0.44
     المسافه
    0.42
    Fav
    0.41
    অ্যাপ
    0.41
     timezone
    0.41
     Organize
    0.40
    公斤
    0.39
    飄
    0.39
     مختلفة
    0.38
    Configuration
    0.38
    POSITIVE LOGITS
    icum
    0.43
    ič
    0.42
    stånd
    0.42
    bleday
    0.40
    ")],
    0.39
    awar
    0.39
     UCLA
    0.39
    ថ្ល
    0.39
    ić
    0.38
     Godfrey
    0.38
    Activations Density 0.001%

    No Known Activations