© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17164
    Prev
    Next
    INDEX
    Explanations

    fall into (stereotypes, patterns, rabbit hole, trap)

    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
     dengan
    0.21
     Same
    0.21
     aynı
    0.21
     dezelfde
    0.21
     Matthew
    0.21
     A
    0.21
     spieg
    0.21
     będą
    0.21
     странице
    0.20
     ugyan
    0.20
    POSITIVE LOGITS
    احت
    0.24
     anses
    0.23
    \{
    0.22
     år
    0.21
    HER
    0.21
    Woods
    0.20
    statt
    0.20
    нат
    0.20
     sump
    0.20
     lawsuit
    0.19
    Activations Density 0.031%

    No Known Activations