© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 83313
    Prev
    Next
    INDEX
    Explanations

    mental health resources

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
    vh
    0.47
    idcar
    0.39
    видно
    0.38
    ésére
    0.38
     Sainsbury
    0.37
    agad
    0.37
     शर
    0.37
    戬
    0.36
     सिक
    0.36
     सिव
    0.35
    POSITIVE LOGITS
    cordova
    0.43
     Lys
    0.42
    Lys
    0.41
     Ionic
    0.40
     botany
    0.39
     ionized
    0.38
    Compact
    0.38
     Qu
    0.37
     oper
    0.37
     optimized
    0.37
    Activations Density 0.041%

    No Known Activations