© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52614
    Prev
    Next
    INDEX
    Explanations

    speaking, giving, leaning, looking

    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
    shield
    0.39
    APR
    0.37
     tears
    0.36
     Tears
    0.35
    希
    0.34
    YS
    0.34
    écriture
    0.34
    Writing
    0.33
     terrified
    0.33
     Shield
    0.33
    POSITIVE LOGITS
    蹬
    0.34
     Pras
    0.32
    唿
    0.32
     ден
    0.32
    思った
    0.30
    筧
    0.30
    薀
    0.30
    peh
    0.29
     curvature
    0.29
    𐰼
    0.29
    Activations Density 0.013%

    No Known Activations