© 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. 221967
    Prev
    Next
    INDEX
    Explanations

    step by step approach

    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
    wel
    0.54
     .
    0.47
     Aliment
    0.46
     Sebuah
    0.46
     О
    0.44
     foment
    0.44
    Wel
    0.44
    筥
    0.43
    "
    0.43
    ulis
    0.43
    POSITIVE LOGITS
    að
    0.57
    ați
    0.55
     đồng
    0.51
    $\--
    0.50
     शायरी
    0.50
     mỹ
    0.50
     preorder
    0.50
    
    0.50
     زين
    0.50
     periódico
    0.49
    Activations Density 0.000%

    No Known Activations