© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12847
    Prev
    Next
    INDEX
    Explanations

    appetite or clear

    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_40_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
    骨
    0.44
     calving
    0.40
     saloon
    0.40
    enhanced
    0.40
     oxygen
    0.39
     stability
    0.38
     shaw
    0.38
    穩定
    0.38
    农
    0.38
    dra
    0.37
    POSITIVE LOGITS
     Compression
    0.73
     compression
    0.72
    Compression
    0.65
    compression
    0.62
     compresses
    0.59
     compress
    0.57
    圧縮
    0.54
    压缩
    0.53
     Compress
    0.51
    Compress
    0.50
    Activations Density 0.088%

    No Known Activations