© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 209859
    Prev
    Next
    INDEX
    Explanations

    Break Russian phrases

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_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
     फांसी
    0.40
    滗
    0.40
    SetValue
    0.39
     estilos
    0.39
    Dieser
    0.37
     đổi
    0.37
    ूण
    0.37
    ETY
    0.37
    Activate
    0.36
     Shifts
    0.36
    POSITIVE LOGITS
     NSP
    0.45
     tramp
    0.38
    ㅈ
    0.37
    npcs
    0.37
    joke
    0.36
    timed
    0.36
     poorly
    0.36
    ()}\
    0.36
     إل
    0.35
    青
    0.35
    Activations Density 0.001%

    No Known Activations