© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34108
    Prev
    Next
    INDEX
    Explanations

    let me know if you'd like me to

    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_31_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
     पाई
    0.46
     позволя
    0.38
    सीमा
    0.37
     Platforms
    0.36
     อยาก
    0.35
     kullanıl
    0.34
    骜
    0.34
     丿
    0.34
     Wearing
    0.34
     layak
    0.34
    POSITIVE LOGITS
    selected
    0.34
    adir
    0.33
    laces
    0.33
    Sans
    0.33
     admitted
    0.32
    jub
    0.32
     selected
    0.31
    altered
    0.31
     души
    0.31
    creates
    0.31
    Activations Density 0.006%

    No Known Activations