© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49224
    Prev
    Next
    INDEX
    Explanations

    foods, nuts

    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_55_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
     snack
    0.51
     spice
    0.47
    甜
    0.44
     Snack
    0.43
     processed
    0.43
     frameworks
    0.43
     spiced
    0.41
     carbohydrates
    0.41
     fruits
    0.40
     মিষ্টি
    0.40
    POSITIVE LOGITS
     Walnut
    0.43
     walnut
    0.42
    ெற்ற
    0.40
     veterinary
    0.39
     Graves
    0.38
    BtnUp
    0.38
    蒺
    0.38
     buffalo
    0.38
     bison
    0.38
     कोतवाली
    0.37
    Activations Density 0.002%

    No Known Activations