© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45589
    Prev
    Next
    INDEX
    Explanations

    digits or numbers

    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_3_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
    ال
    1.03
    t
    0.97
    es
    0.92
    U
    0.85
    L
    0.84
    <0x80>
    0.82
    al
    0.79
    B
    0.75
    eh
    0.74
    ت
    0.73
    POSITIVE LOGITS
     manquer
    0.68
     sanciones
    0.66
     испыта
    0.62
     arbre
    0.62
     измене
    0.61
     unstoppable
    0.61
     analiz
    0.60
     solicita
    0.60
     Pentagon
    0.60
     settimane
    0.59
    Activations Density 0.032%

    No Known Activations