© 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. 125292
    Prev
    Next
    INDEX
    Explanations

    liquid soap and petroleum products

    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
    the
    1.00
    s
    0.93
    л
    0.91
    ف
    0.88
    би
    0.83
    ق
    0.83
    ের
    0.79
    ك
    0.78
    ма
    0.77
    س
    0.77
    POSITIVE LOGITS
    on
    0.67
     comenzó
    0.63
     de
    0.61
    ON
    0.59
     you
    0.59
    at
    0.57
     tik
    0.57
    and
    0.55
    lique
    0.55
     than
    0.55
    Activations Density 0.000%

    No Known Activations