© 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. 36604
    Prev
    Next
    INDEX
    Explanations

    convey meaning or ideas

    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
    im
    0.89
    es
    0.85
    ek
    0.85
    qu
    0.77
    ust
    0.75
    is
    0.74
    a
    0.73
    aw
    0.72
    faktor
    0.71
    त्र
    0.70
    POSITIVE LOGITS
     tertinggi
    0.68
    ۰
    0.62
     discordant
    0.62
    ς
    0.61
     trasc
    0.60
    ی
    0.59
     misinterpreted
    0.57
    意思
    0.57
    <0xB6>
    0.57
     vectorial
    0.56
    Activations Density 0.004%

    No Known Activations