© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45876
    Prev
    Next
    INDEX
    Explanations

    box GL

    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
    ال
    0.72
    ك
    0.68
    ية
    0.64
    ви
    0.64
    غ
    0.63
     of
    0.60
    سته
    0.60
     in
    0.59
    {(
    0.59
    Qs
    0.58
    POSITIVE LOGITS
    ↵
    0.86
    anego
    0.60
    д
    0.60
    า
    0.57
    ↵↵↵↵
    0.56
     COUNT
    0.56
    けます
    0.55
     ​​​​
    0.55
    an
    0.55
    ecia
    0.55
    Activations Density 0.000%

    No Known Activations