© 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. 34820
    Prev
    Next
    INDEX
    Explanations

    pizza, lunch, stone

    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
    in
    0.83
    ки
    0.82
    ו
    0.77
    ي
    0.77
    ف
    0.77
    i
    0.73
    のは
    0.71
    was
    0.70
    ра
    0.68
    G
    0.68
    POSITIVE LOGITS
    .
    0.84
    '
    0.77
     experiments
    0.71
     ailment
    0.67
     ailing
    0.59
    ห
    0.58
    :
    0.56
    প
    0.56
     embodiment
    0.56
     multitude
    0.55
    Activations Density 0.010%

    No Known Activations