© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25540
    Prev
    Next
    INDEX
    Explanations

    similar to

    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_10_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
    '
    0.54
    ל
    0.51
    ↵
    0.50
    惜
    0.49
    ا
    0.47
     qua
    0.46
    تها
    0.46
     connaissance
    0.46
    .
    0.45
     infil
    0.45
    POSITIVE LOGITS
     څنګه
    0.53
     decenas
    0.51
     বাঙ্গালীদের
    0.50
    ak
    0.50
    GEN
    0.50
    {
    0.48
    ৯
    0.48
     ४
    0.48
    }_{
    0.46
    {\
    0.46
    Activations Density 0.023%

    No Known Activations