© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78881
    Prev
    Next
    INDEX
    Explanations

    bot or botany related terms

    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_0_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
    ار
    1.70
    {
    1.64
    at
    1.53
    is
    1.53
    र
    1.48
    т
    1.46
    д
    1.39
    n
    1.38
    to
    1.35
    ों
    1.30
    POSITIVE LOGITS
    1.94
    ud
    1.34
    ك
    1.29
    ના
    1.17
    ка
    1.09
    o
    1.09
    ા
    1.06
    Password
    1.05
    ่ย
    1.02
    itt
    1.00
    Activations Density 0.001%

    No Known Activations