© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42491
    Prev
    Next
    INDEX
    Explanations

    also

    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_13_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
    ляет
    0.27
    ِي
    0.26
    udar
    0.25
     ofthe
    0.25
    다
    0.25
    ást
    0.24
    üren
    0.24
     LAD
    0.23
    스키
    0.23
     construido
    0.23
    POSITIVE LOGITS
    湿
    0.30
    boe
    0.28
    កើត
    0.27
     временем
    0.27
     乀
    0.27
     деятельность
    0.26
    wet
    0.26
    river
    0.26
    بانی
    0.26
    pping
    0.26
    Activations Density 0.006%

    No Known Activations