© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158431
    Prev
    Next
    INDEX
    Explanations

    keyword density notes

    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_2_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
    ن
    0.91
    n
    0.91
    g
    0.88
    ش
    0.86
    어졌
    0.80
    あった
    0.77
    多い
    0.75
    खास्त
    0.74
     The
    0.71
    會
    0.70
    POSITIVE LOGITS
    .
    1.05
    ים
    0.95
    {
    0.86
    ite
    0.83
     einzigen
    0.80
     αλλά
    0.79
    3
    0.79
     of
    0.79
    ↵
    0.79
     endroits
    0.79
    Activations Density 0.004%

    No Known Activations