© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260526
    Prev
    Next
    INDEX
    Explanations

    sudden transition

    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_22_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
     घेत
    0.27
    NgramModel
    0.27
    𐰃
    0.26
     предпо
    0.26
    梗
    0.26
     bloated
    0.26
    夰
    0.25
     wasted
    0.24
     минера
    0.24
     जलवायु
    0.24
    POSITIVE LOGITS
     pagi
    0.29
     நண்ப
    0.29
    pyrazin
    0.28
     lainnya
    0.28
     på
    0.26
     pā
    0.26
    onso
    0.25
     ə
    0.25
     엔
    0.25
     endast
    0.25
    Activations Density 0.004%

    No Known Activations