© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 222628
    Prev
    Next
    INDEX
    Explanations

    return soon or value

    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_10_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
    ت
    1.10
    тся
    0.85
    ।
    0.84
    т
    0.83
    त
    0.81
    hh
    0.78
    I
    0.76
    tt
    0.75
    ু
    0.74
    ü
    0.74
    POSITIVE LOGITS
    ก็
    0.61
     scratching
    0.61
    ۹
    0.60
     tetapi
    0.58
    ရဲ့
    0.58
    nél
    0.57
     topography
    0.57
     workday
    0.56
     quần
    0.55
    子の
    0.54
    Activations Density 0.010%

    No Known Activations