© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 133844
    Prev
    Next
    INDEX
    Explanations

    disabled if component missing

    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_37_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
     extinct
    0.46
     SUCCESSFULLY
    0.43
     Rab
    0.40
     succesfully
    0.39
     ])
    0.39
     Portman
    0.38
     dissolved
    0.38
     killed
    0.38
     Ended
    0.38
     successfully
    0.37
    POSITIVE LOGITS
     adjunct
    0.42
    ography
    0.39
     вес
    0.38
    ancas
    0.38
    Ố
    0.38
    uto
    0.38
    谱
    0.37
     weight
    0.36
     skating
    0.36
    助理
    0.36
    Activations Density 0.001%

    No Known Activations