© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 196459
    Prev
    Next
    INDEX
    Explanations

    food

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    itesse
    0.40
    캅
    0.38
     Uno
    0.38
    孖
    0.37
    臂
    0.37
    ாவை
    0.36
     Communists
    0.36
    محمد
    0.36
    共产党
    0.36
     rinse
    0.35
    POSITIVE LOGITS
    nec
    0.43
    äub
    0.39
    EXPORT
    0.38
    doch
    0.37
    蟄
    0.37
    parrot
    0.37
    uant
    0.36
    রুখ
    0.36
     particulière
    0.36
    UK
    0.35
    Activations Density 0.001%

    No Known Activations