© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35246
    Prev
    Next
    INDEX
    Explanations

    landing

    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_3_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
    ر
    0.97
    ان
    0.86
    т
    0.82
    ل
    0.80
    ր
    0.78
    ad
    0.73
    िया
    0.73
    ير
    0.70
    ت
    0.70
    на
    0.70
    POSITIVE LOGITS
     in
    0.86
     vinden
    0.70
    도
    0.67
     Landry
    0.66
    ใน
    0.66
     سپس
    0.65
     ਫ
    0.64
    ช่วง
    0.63
     לנ
    0.61
     ▸
    0.60
    Activations Density 0.019%

    No Known Activations