© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57072
    Prev
    Next
    INDEX
    Explanations

    comprobar, prueba, probable

    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_11_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
    <0x0D>
    0.71
     hadc
    0.67
    i
    0.65
     {
    0.64
    ُ
    0.62
     avait
    0.61
    <b>
    0.61
     benzer
    0.59
    </b>
    0.59
     W
    0.59
    POSITIVE LOGITS
    eliers
    0.55
    Unis
    0.54
    Neurons
    0.52
    leges
    0.52
    зре
    0.52
    elems
    0.52
    гут
    0.50
    다고
    0.50
     Karlsson
    0.50
    emat
    0.50
    Activations Density 0.000%

    No Known Activations