© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 203667
    Prev
    Next
    INDEX
    Explanations

    quick

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     yet
    0.49
     eating
    0.44
     fast
    0.44
    Eating
    0.43
     快
    0.42
     Eating
    0.41
    yet
    0.41
    饮食
    0.41
     Fast
    0.39
    飲食
    0.39
    POSITIVE LOGITS
     bite
    0.54
    bite
    0.45
     /
    0.44
     Bite
    0.44
    Alternative
    0.40
    music
    0.39
     Smoke
    0.38
     Alternative
    0.38
    立った
    0.38
    alternative
    0.37
    Activations Density 0.001%

    No Known Activations