© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 206200
    Prev
    Next
    INDEX
    Explanations

    ending disruptions

    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_19_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
     Familie
    0.52
     Minneapolis
    0.50
    ين
    0.47
     Hinweise
    0.45
     ihre
    0.45
    進
    0.45
     Massimo
    0.45
     Ver
    0.44
    forcer
    0.44
     kanilang
    0.44
    POSITIVE LOGITS
    ENDING
    0.68
    editar
    0.46
     irregular
    0.46
    puesta
    0.46
     optically
    0.46
     impairment
    0.45
    Enviar
    0.45
    est
    0.45
    ل
    0.45
    ending
    0.44
    Activations Density 0.000%

    No Known Activations