© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 151822
    Prev
    Next
    INDEX
    Explanations

    controller, review, spectral, Creator, hosts, master

    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_18_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
     ಪರಿಸ
    0.55
     پایان
    0.51
     endGame
    0.50
    㻐
    0.49
     ಕಂಚ
    0.48
     문제는
    0.48
     ending
    0.47
    стал
    0.47
     ended
    0.47
     gameOver
    0.47
    POSITIVE LOGITS
    Altitude
    0.50
    Schema
    0.46
    providing
    0.46
    t
    0.46
    s
    0.46
    Obs
    0.46
    _
    0.46
    ships
    0.44
     physicians
    0.43
     Schema
    0.42
    Activations Density 0.000%

    No Known Activations