© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18768
    Prev
    Next
    INDEX
    Explanations

    social work and assistance programs

    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_34_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
     Kyrgyz
    0.40
     Angles
    0.38
     Serp
    0.37
     Bianchi
    0.37
     refractive
    0.37
     sterility
    0.36
    穆
    0.36
    repaint
    0.35
     />,
    0.34
    Bump
    0.33
    POSITIVE LOGITS
     caseworker
    0.60
     social
    0.60
     соціа
    0.59
    児童
    0.58
     sociaux
    0.57
    social
    0.56
     Sozial
    0.55
     sociales
    0.55
     sociale
    0.55
     sosyal
    0.55
    Activations Density 0.022%

    No Known Activations