© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246956
    Prev
    Next
    INDEX
    Explanations

    for your

    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_40_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
     deewana
    0.41
     Bxd
    0.39
    Ante
    0.38
    istar
    0.38
    Zw
    0.37
    评标
    0.37
    agem
    0.37
    헐
    0.36
    star
    0.36
     পাকসেন
    0.36
    POSITIVE LOGITS
     titel
    0.41
    Leaving
    0.37
     relies
    0.37
    话题
    0.37
     Consciousness
    0.37
     costi
    0.37
     Accepts
    0.37
    რთ
    0.36
     bewust
    0.36
    rainer
    0.36
    Activations Density 0.002%

    No Known Activations