© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127178
    Prev
    Next
    INDEX
    Explanations

    **changes**

    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_37_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
     moved
    2.03
     relocated
    1.93
    移
    1.81
     Moved
    1.79
    moved
    1.77
     relocate
    1.76
     relocation
    1.73
    Moved
    1.71
     relocating
    1.68
     reloc
    1.64
    POSITIVE LOGITS
     gäller
    0.37
    فاوت
    0.37
    ätzung
    0.37
     swirls
    0.36
     niedrig
    0.35
    羲
    0.34
     Guaranteed
    0.34
     написал
    0.34
    ۆر
    0.33
    čním
    0.33
    Activations Density 0.043%

    No Known Activations