© 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. 123302
    Prev
    Next
    INDEX
    Explanations

    internet access, technologies, debate, moment

    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
    '
    0.65
    ון
    0.63
    "
    0.63
    ينة
    0.59
     engages
    0.59
     libri
    0.58
     articul
    0.57
     multiplies
    0.57
     detects
    0.57
     conveys
    0.57
    POSITIVE LOGITS
    ك
    0.86
    ل
    0.73
    म
    0.71
    ри
    0.70
    ಿಯೇ
    0.68
    на
    0.67
    constructing
    0.66
    viral
    0.64
    ون
    0.63
    heated
    0.63
    Activations Density 0.002%

    No Known Activations