© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125599
    Prev
    Next
    INDEX
    Explanations

    digital circuits and light

    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
    o
    0.92
    u
    0.89
    i
    0.71
    ads
    0.69
    bben
    0.66
    cimientos
    0.65
     Innovations
    0.64
    z
    0.64
    aciones
    0.62
    b
    0.62
    POSITIVE LOGITS
    ’
    0.97
     ສຳ
    0.74
    ྜ
    0.65
     utilize
    0.64
    siniz
    0.64
    Ğ
    0.64
     tutt
    0.62
    ");
    0.61
     vă
    0.61
    PE
    0.61
    Activations Density 0.012%

    No Known Activations