© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91140
    Prev
    Next
    INDEX
    Explanations

    if you

    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_11_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
    f
    0.67
    v
    0.67
     Recent
    0.66
     Hö
    0.64
    ar
    0.60
     Biographical
    0.59
     Harlem
    0.59
     हळ
    0.59
     त्यांची
    0.58
     Racine
    0.58
    POSITIVE LOGITS
    ,
    0.75
    leszt
    0.58
     slay
    0.54
     shap
    0.53
    FAA
    0.52
     shop
    0.50
     critters
    0.50
     nob
    0.50
    ORTYPE
    0.50
    Laundry
    0.50
    Activations Density 0.009%

    No Known Activations