© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56807
    Prev
    Next
    INDEX
    Explanations

    giggled

    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_11_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
    اپ
    0.71
    ﺖ
    0.64
     ਚ
    0.62
    ρια
    0.61
    Record
    0.60
     strawberry
    0.59
    OPA
    0.58
    acters
    0.57
     آهنگ
    0.57
     cypress
    0.57
    POSITIVE LOGITS
    ja
    0.66
    дә
    0.60
     ofte
    0.59
    धीन
    0.58
    ն
    0.57
    ке
    0.54
    ال
    0.54
    -
    0.53
     educators
    0.53
    ieke
    0.53
    Activations Density 0.001%

    No Known Activations