© 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. 200967
    Prev
    Next
    INDEX
    Explanations

    artificial light, sweeteners, environments

    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
     artificial
    0.40
     gi
    0.38
     fake
    0.37
     faux
    0.36
     toán
    0.36
    шении
    0.36
     bogus
    0.36
    ޔ
    0.36
     pseudo
    0.35
     imitate
    0.35
    POSITIVE LOGITS
    Superview
    0.41
    superclass
    0.39
    Developing
    0.38
    مراجع
    0.37
    Nor
    0.37
    GENER
    0.37
     Developing
    0.37
     Seismic
    0.36
    強力
    0.36
    COUVER
    0.36
    Activations Density 0.002%

    No Known Activations