© 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. 220057
    Prev
    Next
    INDEX
    Explanations

    fluorescence, light, photoluminescence

    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
    ष्मा
    0.42
    苼
    0.40
     prominently
    0.38
     Filmm
    0.38
     فیلم
    0.38
    mostat
    0.37
    Film
    0.37
    chea
    0.37
     Congress
    0.37
    Artist
    0.37
    POSITIVE LOGITS
    тики
    0.39
     lauf
    0.37
     timeliness
    0.37
     wrap
    0.36
    λ
    0.35
     বাংলাকে
    0.35
     wra
    0.34
    тем
    0.34
    timeline
    0.34
     PROTE
    0.33
    Activations Density 0.001%

    No Known Activations