© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 66623
    Prev
    Next
    INDEX
    Explanations

    food ingredients

    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_46_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
    ૮
    0.40
     soaring
    0.37
    mapKey
    0.35
     น้ํา
    0.35
    did
    0.34
    ின
    0.34
    Germany
    0.34
    rewrite
    0.34
     buzz
    0.34
     बांध
    0.34
    POSITIVE LOGITS
     Contrast
    0.40
    棰
    0.39
    ঘ্র
    0.39
    плуа
    0.39
     ওয়েস্ট
    0.39
     print
    0.38
     Harvard
    0.37
     আমেরিকান
    0.37
     Eck
    0.37
     Ch
    0.36
    Activations Density 0.005%

    No Known Activations