© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194455
    Prev
    Next
    INDEX
    Explanations

    inconvenience, sides, not exist, moves, point to, mail, pre, ienes sociales

    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_15_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
    mprj
    0.54
     vipp
    0.53
    irons
    0.52
     ď
    0.52
    rusty
    0.52
     semelh
    0.51
    andfeel
    0.51
    moss
    0.51
    讽
    0.51
    iron
    0.51
    POSITIVE LOGITS
    أة
    0.48
     تضيفلها
    0.47
    <h6>
    0.46
     uč
    0.46
     threat
    0.46
    突然
    0.46
     مصر
    0.45
    国际
    0.45
    量的
    0.44
     {
    0.44
    Activations Density 0.000%

    No Known Activations