© 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
    2. Gemma-3-27B-IT
    3. 59-GEMMASCOPE-2-TRANSCODER-262K
    4. 61047
    Prev
    Next
    INDEX
    Explanations

    foreign characters

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    elry
    0.33
    ]
    0.32
    \}
    0.31
    oubt
    0.31
    raintree
    0.30
    nesday
    0.30
    ancellationToken
    0.29
    rtle
    0.29
    lassical
    0.29
    ?
    0.28
    POSITIVE LOGITS
    ᐋ
    0.32
    ൪
    0.31
    ڎ
    0.29
    禇
    0.29
     privés
    0.28
     légende
    0.28
    퐶
    0.28
     प्रीम
    0.27
     PLA
    0.27
     *_
    0.27
    Activations Density 0.007%

    No Known Activations