© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221711
    Prev
    Next
    INDEX
    Explanations

    prayer for

    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_10_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
     prayer
    0.34
    ,
    0.34
    ু
    0.27
    ี
    0.26
     молит
    0.26
    ف
    0.26
     модель
    0.25
    н
    0.25
    ι
    0.25
     to
    0.25
    POSITIVE LOGITS
    rène
    0.30
    dicke
    0.30
    in
    0.29
    sinh
    0.29
    splitting
    0.27
    spreading
    0.25
    s
    0.25
    rate
    0.25
    operating
    0.25
    springen
    0.25
    Activations Density 0.002%

    No Known Activations