© 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. 57889
    Prev
    Next
    INDEX
    Explanations

    query agenda or to-do list

    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
    en
    0.70
    োতে
    0.53
    Work
    0.52
     Schmitt
    0.52
    <h4>
    0.51
     (
    0.51
     Seasonal
    0.51
    ou
    0.50
     by
    0.50
     $|
    0.50
    POSITIVE LOGITS
    את
    0.69
     effettuare
    0.67
     alterar
    0.65
    عی
    0.64
    ط
    0.64
    تر
    0.64
    شک
    0.63
    合せ
    0.62
     actuaciones
    0.62
    트
    0.62
    Activations Density 0.002%

    No Known Activations