© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218458
    Prev
    Next
    INDEX
    Explanations

    few examples

    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_31_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
     కరో
    0.37
     ricerc
    0.36
     imme
    0.36
     দাদা
    0.35
    ጃ
    0.34
    INTE
    0.33
    デル
    0.33
     agam
    0.33
    觟
    0.33
    基因
    0.32
    POSITIVE LOGITS
    或其他
    0.33
     job
    0.31
     inhibitors
    0.31
     actuators
    0.30
    ул
    0.30
    ствии
    0.29
     determinadas
    0.29
    的其他
    0.29
    nash
    0.29
     other
    0.29
    Activations Density 0.002%

    No Known Activations