© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48503
    Prev
    Next
    INDEX
    Explanations

    it's easy / tempting / important

    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
     Leuk
    0.43
     multid
    0.37
    schod
    0.36
     thus
    0.36
     flexibility
    0.35
    が一
    0.35
     twofold
    0.35
    绯
    0.35
     प्रकृति
    0.34
     compact
    0.34
    POSITIVE LOGITS
     позже
    0.37
     позднее
    0.35
    ेश्वर
    0.33
     sırasında
    0.33
     районе
    0.32
     malheureusement
    0.31
     xD
    0.31
     подразуме
    0.31
    컷
    0.31
    sources
    0.30
    Activations Density 0.004%

    No Known Activations