© 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. 127066
    Prev
    Next
    INDEX
    Explanations

    Mapper, Council, Army, cpp, JS, dust

    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
    la
    0.99
    ﺭ
    0.79
     that
    0.78
    l
    0.78
    lo
    0.77
    ת
    0.77
    ing
    0.75
    其他
    0.75
    ↵
    0.75
    ла
    0.75
    POSITIVE LOGITS
    ƅ
    0.71
     됐
    0.67
    鿆
    0.66
    劦
    0.66
     сестра
    0.64
    叐
    0.64
    ashita
    0.62
    ўкі
    0.61
     заяви
    0.61
    agangan
    0.60
    Activations Density 0.022%

    No Known Activations