© 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
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36592
    Prev
    Next
    INDEX
    Explanations

    Holy Trinity and Walk of Fame

    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
    at
    0.88
    an
    0.87
    are
    0.83
    ig
    0.79
    il
    0.75
    ای
    0.74
    ine
    0.70
    _
    0.68
    set
    0.65
    l
    0.64
    POSITIVE LOGITS
    )
    0.64
    ли
    0.64
    ంగా
    0.61
    دأ
    0.59
    :
    0.57
    דת
    0.55
    ğini
    0.54
    تمي
    0.54
    首都
    0.53
     действи
    0.52
    Activations Density 0.001%

    No Known Activations