© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142395
    Prev
    Next
    INDEX
    Explanations

    Belém Tower

    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_12_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
    ts
    0.68
    i
    0.59
    arla
    0.58
    0.57
    safety
    0.54
    therapy
    0.54
    fir
    0.54
    l
    0.53
    oxin
    0.53
    ttt
    0.53
    POSITIVE LOGITS
     Remain
    0.54
     Agnes
    0.51
     Estes
    0.51
     Portuguese
    0.50
     Exchanges
    0.49
     bloke
    0.49
     USB
    0.48
     Sejam
    0.48
     முன்
    0.48
     Danes
    0.47
    Activations Density 0.000%

    No Known Activations