© 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. 42165
    Prev
    Next
    INDEX
    Explanations

    blessings and divine requests

    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
    ט
    1.04
    ين
    0.84
    이다
    0.82
    트
    0.82
    ле
    0.80
    ম
    0.79
    ли
    0.78
    اب
    0.73
    ൻ
    0.73
    ло
    0.72
    POSITIVE LOGITS
    hesians
    0.71
    本日
    0.69
    一个月
    0.67
    ปี
    0.65
     system
    0.64
    inink
    0.63
     infringement
    0.63
    violet
    0.63
     fabrics
    0.62
    \
    0.62
    Activations Density 0.013%

    No Known Activations