© 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. 174236
    Prev
    Next
    INDEX
    Explanations

    random generation code

    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
     feu
    0.43
     خون
    0.42
     concert
    0.41
    会い
    0.40
    処
    0.40
    Setting
    0.40
    atul
    0.40
     Zor
    0.39
    нуу
    0.39
    Tent
    0.39
    POSITIVE LOGITS
    ,”
    0.45
    这样做
    0.45
     comigo
    0.43
    ريبات
    0.42
    ​,
    0.42
     FPS
    0.41
    بس
    0.41
     સમજ
    0.41
     wrath
    0.41
    饮料
    0.41
    Activations Density 0.003%

    No Known Activations