© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 19154
    Prev
    Next
    INDEX
    Explanations

    hallucinations, mistaken, inventing

    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_34_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
    বারে
    0.38
     reproducción
    0.37
     العد
    0.35
     elección
    0.34
     liu
    0.34
     añadir
    0.34
     benc
    0.33
     노트
    0.33
    𒆪
    0.33
    ܝܢ
    0.33
    POSITIVE LOGITS
     pretending
    0.75
     pretended
    0.73
     pretend
    0.69
     falsely
    0.67
     prét
    0.67
     claiming
    0.66
     pretends
    0.66
    pret
    0.62
     claimed
    0.58
     pret
    0.57
    Activations Density 0.117%

    No Known Activations