© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62517
    Prev
    Next
    INDEX
    Explanations

    bank teller

    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_11_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
    7
    0.62
    5
    0.54
    8
    0.52
    ۸
    0.52
     increases
    0.48
     séries
    0.48
     MCL
    0.47
    t
    0.47
    4
    0.46
     bumps
    0.46
    POSITIVE LOGITS
    ين
    0.68
    鉐
    0.67
     vervolgens
    0.65
     Russische
    0.61
     Anschließend
    0.59
     письмен
    0.58
     remembr
    0.57
     schrift
    0.57
     Schrift
    0.57
     Sicherheits
    0.56
    Activations Density 0.000%

    No Known Activations