© 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. 177381
    Prev
    Next
    INDEX
    Explanations

    responsible for negative impacts

    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
    благо
    0.45
    ರವ
    0.43
    箫
    0.41
     adaptación
    0.41
    utilisation
    0.41
     рекомендуется
    0.40
    тык
    0.40
     thanking
    0.39
    一张
    0.38
    簫
    0.38
    POSITIVE LOGITS
     inventors
    0.39
     philosophers
    0.38
     imm
    0.37
     tag
    0.36
    ｹ
    0.36
     philosopher
    0.35
     directly
    0.35
     gains
    0.35
    ['-
    0.35
     persistently
    0.35
    Activations Density 0.002%

    No Known Activations