© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122644
    Prev
    Next
    INDEX
    Explanations

    fulham or phulavati

    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_3_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
     سلي
    0.73
    0.67
             
    0.66
              
    0.66
    Gesch
    0.66
    並且
    0.66
    㫜
    0.66
     Česk
    0.65
    0.64
     İstifadə
    0.63
    POSITIVE LOGITS
     as
    1.13
    are
    1.12
     are
    1.11
     for
    1.00
    s
    0.94
    ons
    0.80
    ियों
    0.79
    el
    0.78
    ENT
    0.78
    itty
    0.78
    Activations Density 0.000%

    No Known Activations