© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126186
    Prev
    Next
    INDEX
    Explanations

    price trends

    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_3_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
    ی
    0.90
    انی
    0.83
    ᱐
    0.83
    ᱓
    0.79
    த்தில்
    0.77
    ینی
    0.76
    ⅾ
    0.75
    orderInCategory
    0.74
    ставить
    0.74
    عنی
    0.74
    POSITIVE LOGITS
     an
    0.89
     (
    0.81
     in
    0.79
     %
    0.77
     spring
    0.76
     side
    0.75
    ting
    0.75
     a
    0.74
    ta
    0.74
     header
    0.73
    Activations Density 0.001%

    No Known Activations