© 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. 4940
    Prev
    Next
    INDEX
    Explanations

    import statements

    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
     வரைய
    0.31
     영업
    0.30
    TabIndex
    0.28
     ಅದರ
    0.28
     مش
    0.28
    സ്യ
    0.28
    豁
    0.27
    䣵
    0.27
     المش
    0.27
    мыш
    0.26
    POSITIVE LOGITS
    type
    0.48
    const
    0.45
     type
    0.42
     Const
    0.42
     const
    0.39
    Const
    0.37
     konst
    0.32
     نوع
    0.32
     tipo
    0.32
    trait
    0.32
    Activations Density 0.004%

    No Known Activations