© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78927
    Prev
    Next
    INDEX
    Explanations

    harmful and violates

    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_31_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
     Kir
    0.36
     rufis
    0.35
     ]);
    0.35
     निर्देशों
    0.34
    ulka
    0.34
     remarked
    0.34
    蒡
    0.33
     折
    0.33
     தாய
    0.33
    mla
    0.33
    POSITIVE LOGITS
     poverty
    0.38
     incredibly
    0.36
     plausible
    0.36
     insuf
    0.35
     creation
    0.35
    display
    0.34
     представления
    0.33
     المثال
    0.33
    }\{
    0.33
     favour
    0.32
    Activations Density 0.031%

    No Known Activations