© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201948
    Prev
    Next
    INDEX
    Explanations

    if questions

    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_12_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
    </h3>
    0.62
    ડ
    0.60
    സ
    0.55
     Doyle
    0.54
    И
    0.54
    ણ
    0.54
    危険
    0.53
    ق
    0.52
     ト
    0.51
    ט
    0.51
    POSITIVE LOGITS
    kab
    0.54
    ítani
    0.54
    ocommerce
    0.52
    pane
    0.52
    stag
    0.50
     বাড়তি
    0.50
    AI
    0.49
    kring
    0.49
    om
    0.49
    veer
    0.49
    Activations Density 0.002%

    No Known Activations