© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 5708
    Prev
    Next
    INDEX
    Explanations

    more detailed

    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_40_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
     more
    1.70
     lebih
    1.60
     более
    1.59
     bardziej
    1.55
     better
    1.55
     більш
    1.53
    更
    1.46
     יותר
    1.45
     más
    1.43
     più
    1.43
    POSITIVE LOGITS
     hd
    0.35
    culas
    0.35
     Haver
    0.34
    lass
    0.33
     Qian
    0.33
    Ⲱ
    0.33
     Plasma
    0.32
    हूर
    0.32
    采
    0.32
    ómago
    0.31
    Activations Density 0.272%

    No Known Activations