© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51345
    Prev
    Next
    INDEX
    Explanations

    misleading or incorrect statements

    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_30_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
     sawa
    0.48
     सराहना
    0.38
    优
    0.38
     Mad
    0.37
     प्रतीत
    0.37
    츄
    0.37
    yama
    0.37
    ayan
    0.36
    নকে
    0.36
     MDA
    0.36
    POSITIVE LOGITS
     제대로
    0.38
    激
    0.37
     grat
    0.35
     capazes
    0.34
    KindOfClass
    0.34
     imposing
    0.33
     capable
    0.32
    íses
    0.32
    全力
    0.32
    Dramatic
    0.32
    Activations Density 0.019%

    No Known Activations