© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1051
    Prev
    Next
    INDEX
    Explanations

    biological and metabolic processes

    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_39_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
    晞
    0.41
     clínico
    0.38
    щика
    0.37
    位数
    0.36
    Subjects
    0.36
    hayati
    0.36
    ິນ
    0.36
    Hist
    0.36
    ],//
    0.36
     Appropriations
    0.36
    POSITIVE LOGITS
     reactions
    0.49
     mediators
    0.41
     seascape
    0.40
     beachfront
    0.40
     cascade
    0.39
     reactivity
    0.39
    icol
    0.38
     burnt
    0.37
     refin
    0.37
     cleft
    0.37
    Activations Density 0.056%

    No Known Activations