© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44900
    Prev
    Next
    INDEX
    Explanations

    following technical documentation

    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_13_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
    ){
    0.52
     Montserrat
    0.50
    </strong>
    0.48
     판
    0.47
     Nghi
    0.47
    import
    0.47
     찬
    0.46
     令
    0.46
     int
    0.46
     선
    0.46
    POSITIVE LOGITS
    ene
    0.55
    ين
    0.52
    мпа
    0.49
    detected
    0.49
     архив
    0.47
     প্রতিক্রি
    0.47
    мий
    0.46
    蒌
    0.46
    يته
    0.46
    推进
    0.45
    Activations Density 0.000%

    No Known Activations