© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 77284
    Prev
    Next
    INDEX
    Explanations

    then followed by certain words

    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_29_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
     marginalised
    0.41
     BEEN
    0.39
    вет
    0.37
    haviour
    0.36
    Behaviour
    0.36
     tenements
    0.36
     😂😂
    0.36
    یە
    0.36
     neighbouring
    0.35
     oes
    0.35
    POSITIVE LOGITS
     старо
    0.40
    NewGuid
    0.39
     ізо
    0.38
     pili
    0.37
     витра
    0.36
    스티
    0.35
    фіка
    0.35
    ण्या
    0.35
    QX
    0.34
    夸
    0.34
    Activations Density 0.000%

    No Known Activations