© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137668
    Prev
    Next
    INDEX
    Explanations

    last

    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
     MILLER
    0.55
    اديه
    0.48
     табли
    0.47
    كي
    0.46
     concedes
    0.46
     devrez
    0.45
    '
    0.44
     allocated
    0.44
    рый
    0.44
     snel
    0.43
    POSITIVE LOGITS
    सर
    0.52
    $
    0.50
    .<
    0.50
    OL
    0.48
    ar
    0.48
    ल्स
    0.48
     वाढ
    0.48
     သ
    0.48
    Sunglasses
    0.46
    AJ
    0.46
    Activations Density 0.001%

    No Known Activations