© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 21
    Prev
    Next
    INDEX
    Explanations

    foreign names or options

    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_40_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
    亢
    0.29
     mant
    0.29
    
    0.29
    চার
    0.27
     mv
    0.27
     ста
    0.26
    permalink
    0.26
     конце
    0.26
    孕
    0.26
    Looking
    0.26
    POSITIVE LOGITS
    aku
    0.35
     Moran
    0.34
    オプション
    0.33
    azu
    0.31
    ब्बत
    0.31
    akka
    0.30
     Ambedkar
    0.30
     options
    0.29
    Options
    0.29
    yní
    0.29
    Activations Density 0.011%

    No Known Activations