© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198942
    Prev
    Next
    INDEX
    Explanations

    Potassium, Glycerol, Dove, ingredients

    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_12_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
    ן
    0.43
    </strong>
    0.36
    nese
    0.34
    ண்ட
    0.33
    </em>
    0.32
     kecil
    0.32
    el
    0.32
    nan
    0.32
     covering
    0.31
    <0xA8>
    0.31
    POSITIVE LOGITS
     oiseaux
    0.44
     Aladdin
    0.41
     Allemagne
    0.41
     Alors
    0.38
     Möglich
    0.38
     Cependant
    0.38
    画像を
    0.38
     Horus
    0.38
     lieux
    0.37
     Marlene
    0.37
    Activations Density 0.006%

    No Known Activations