© 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. 37749
    Prev
    Next
    INDEX
    Explanations

    sandstone, sandviches, dunes

    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
    годи
    0.80
    код
    0.70
    ዚያ
    0.64
    ஜீ
    0.63
    <0xD1>
    0.62
    Tôi
    0.61
     জল
    0.60
     കൂടുതൽ
    0.60
     jeunesse
    0.60
    厘米
    0.59
    POSITIVE LOGITS
    ing
    1.10
    f
    0.89
    n
    0.88
    s
    0.88
    ्स
    0.81
     to
    0.81
    ش
    0.79
    ;
    0.79
    ↵↵
    0.77
    िंग
    0.77
    Activations Density 0.001%

    No Known Activations