© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18291
    Prev
    Next
    INDEX
    Explanations

    you heard that right

    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
     populations
    0.52
     impactful
    0.49
    ImageBeforeText
    0.49
     eficaz
    0.48
    驍
    0.47
     discrete
    0.47
     meaningful
    0.46
    \
    0.46
     significativa
    0.46
    この
    0.46
    POSITIVE LOGITS
     Julia
    0.60
    jek
    0.55
     Gregory
    0.55
     welke
    0.55
    ør
    0.55
    friday
    0.55
     Tyler
    0.53
     Spes
    0.53
     karşınız
    0.52
     chatting
    0.51
    Activations Density 0.006%

    No Known Activations