© 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. 35178
    Prev
    Next
    INDEX
    Explanations

    green light, star, pepper, day, power, powder

    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
    ح
    0.68
    ant
    0.68
    t
    0.65
    ت
    0.65
     I
    0.64
    ik
    0.64
    િ
    0.63
    et
    0.63
    ي
    0.61
     r
    0.61
    POSITIVE LOGITS
    동
    0.69
    ુ
    0.63
     integrante
    0.61
    會
    0.60
    傥
    0.60
     الحاله
    0.59
    자로
    0.58
    전자
    0.58
    주고
    0.58
     Hrvatske
    0.57
    Activations Density 0.003%

    No Known Activations