© 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. 56445
    Prev
    Next
    INDEX
    Explanations

    en el caso de

    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
     nyc
    0.65
     你
    0.64
     Listen
    0.62
     通过
    0.62
     Antit
    0.62
    </h4>
    0.61
     setzen
    0.61
    產生
    0.60
     ascol
    0.60
     美国
    0.60
    POSITIVE LOGITS
    t
    0.59
     purportedly
    0.54
    यों
    0.53
    añas
    0.53
    ELSE
    0.51
    ,’
    0.51
    ,’’
    0.51
    vstack
    0.50
     परेशानियों
    0.50
    elum
    0.50
    Activations Density 0.000%

    No Known Activations