© 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. 209455
    Prev
    Next
    INDEX
    Explanations

    feature importance ranking

    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
     ανάπτυ
    0.48
     Manual
    0.44
    含义
    0.44
     विज्ञान
    0.44
    ℧
    0.43
     UHF
    0.42
     adhé
    0.42
     stewards
    0.41
     과학
    0.41
     руках
    0.41
    POSITIVE LOGITS
    쥴
    0.43
     tudo
    0.41
    সরকারী
    0.41
    ائے
    0.39
     charitable
    0.39
    忘れ
    0.39
    arrerol
    0.39
    還可以
    0.39
     çöze
    0.38
    私の
    0.38
    Activations Density 0.002%

    No Known Activations