© 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. 41233
    Prev
    Next
    INDEX
    Explanations

    International or non-Latin scripts

    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
    q
    0.80
    ;
    0.75
    .,
    0.75
    .\
    0.74
    ade
    0.73
    ock
    0.72
    o
    0.72
    >
    0.70
    all
    0.70
    ber
    0.70
    POSITIVE LOGITS
     لیګ
    0.78
    ת
    0.74
    يد
    0.73
    ين
    0.72
     اصلي
    0.71
    يق
    0.71
    ів
    0.70
    ták
    0.70
    اك
    0.69
    ك
    0.67
    Activations Density 0.005%

    No Known Activations