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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86770
    Prev
    Next
    INDEX
    Explanations

    reports from sources

    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_23_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
     lParam
    0.40
     solen
    0.38
    മ്പർ
    0.37
    釦
    0.36
    ladı
    0.36
    риал
    0.36
     ederim
    0.36
    pperware
    0.36
     Pellet
    0.35
     gráfico
    0.35
    POSITIVE LOGITS
     fauna
    0.38
     ο
    0.38
    雋
    0.37
    度
    0.36
    仰
    0.34
    二
    0.34
    وو
    0.33
     ман
    0.33
     boyfriend
    0.33
     bequeathed
    0.32
    Activations Density 0.002%

    No Known Activations