© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161200
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis

    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_31_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
    apest
    0.38
     triglyceride
    0.36
    晝
    0.35
    AFP
    0.34
    ONS
    0.34
     Naomi
    0.33
    fits
    0.33
     AFP
    0.33
     incongru
    0.33
    ACG
    0.32
    POSITIVE LOGITS
    ်
    0.43
     preferences
    0.41
     locations
    0.41
    咛
    0.41
     Agreements
    0.40
     compds
    0.40
     Área
    0.40
     landings
    0.39
    好
    0.39
     nominations
    0.39
    Activations Density 0.001%

    No Known Activations