© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17366
    Prev
    Next
    INDEX
    Explanations

    #!/ shebangs

    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_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Supplements
    0.43
    pieceSelection
    0.42
     electrón
    0.41
     entrou
    0.40
     hadrons
    0.39
    
    0.38
    りました
    0.38
     ذوالفقار
    0.38
     యు
    0.38
    ร้อม
    0.38
    POSITIVE LOGITS
     links
    0.45
     user
    0.43
     systemic
    0.42
     User
    0.41
     Capitol
    0.41
     У
    0.40
     capitol
    0.39
    User
    0.38
     past
    0.38
    amore
    0.37
    Activations Density 0.002%

    No Known Activations