© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230156
    Prev
    Next
    INDEX
    Explanations

    Hebrew words and characters

    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_6_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
    ंना
    0.90
    ere
    0.88
    _
    0.88
    name
    0.85
    cafe
    0.85
    gget
    0.85
    ंनी
    0.84
    ंमुळे
    0.83
    acht
    0.82
    quantile
    0.82
    POSITIVE LOGITS
    ب
    1.48
    ف
    1.29
    <0x0D>
    1.23
    о
    1.13
    ז
    1.11
    يد
    1.07
    и
    1.07
    </b>
    1.05
    </h4>
    1.02
    。</
    1.00
    Activations Density 0.000%

    No Known Activations