© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27876
    Prev
    Next
    INDEX
    Explanations

    materials science

    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_10_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
    腺
    0.73
    8
    0.64
    ᐈ
    0.62
     cautions
    0.61
    少ない
    0.60
    ắn
    0.59
     pleases
    0.59
     présents
    0.58
    医師
    0.57
     marches
    0.57
    POSITIVE LOGITS
    ل
    0.72
    ot
    0.71
     metallurgy
    0.69
     life
    0.68
     życie
    0.68
    ol
    0.66
     жизнь
    0.66
     metallurgical
    0.64
    ț
    0.64
     Inst
    0.63
    Activations Density 0.004%

    No Known Activations