© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120482
    Prev
    Next
    INDEX
    Explanations

    respectively / respectivamente

    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_27_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
    piece
    0.42
    branchNode
    0.41
    ceived
    0.35
    branch
    0.35
     =-\
    0.35
    serialize
    0.35
    자를
    0.34
    eseed
    0.34
    addressed
    0.34
     généralement
    0.34
    POSITIVE LOGITS
    ̣
    0.43
     चित
    0.41
     needing
    0.41
     неу
    0.40
     Mg
    0.39
     Mö
    0.39
     Syllabus
    0.39
     aspart
    0.38
     exams
    0.38
     Curly
    0.38
    Activations Density 0.001%

    No Known Activations