© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4558
    Prev
    Next
    INDEX
    Explanations

    private equity firms

    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
     пато
    0.36
    ')";
    0.35
    iellement
    0.35
    лит
    0.34
    FName
    0.34
     வாக
    0.33
    ảm
    0.33
     Pint
    0.33
     آل
    0.33
    🅽
    0.33
    POSITIVE LOGITS
     private
    1.84
     Private
    1.70
    Private
    1.63
    private
    1.59
     PRIVATE
    1.50
    私
    1.46
     प्राइवेट
    1.38
     निजी
    1.35
    PRIVATE
    1.32
     私
    1.29
    Activations Density 0.014%

    No Known Activations