© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16730
    Prev
    Next
    INDEX
    Explanations

    programming toolkits and concepts

    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_15_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
    ździer
    0.60
     nào
    0.58
     estavam
    0.58
     पाण्या
    0.56
     foram
    0.55
     كانوا
    0.55
     ص
    0.55
     ві
    0.54
     తా
    0.54
    </h4>
    0.54
    POSITIVE LOGITS
     Leute
    0.47
     Museum
    0.45
     cura
    0.44
    line
    0.44
    莳
    0.43
     Fotograf
    0.43
    aler
    0.42
     docente
    0.42
     Chiu
    0.42
     Mayor
    0.41
    Activations Density 0.000%

    No Known Activations