© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 21435
    Prev
    Next
    INDEX
    Explanations

    food/recipes

    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_56_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
     perfectly
    0.42
    atering
    0.42
    ан
    0.39
    անք
    0.38
    iffent
    0.38
    惩
    0.38
    ellent
    0.37
    वाहक
    0.37
     flawlessly
    0.36
     Coleman
    0.36
    POSITIVE LOGITS
    力
    0.40
     Guess
    0.39
    өө
    0.38
    onet
    0.36
    Quad
    0.36
    צה
    0.35
    Shirts
    0.35
    store
    0.35
    Quiz
    0.35
    上の
    0.34
    Activations Density 0.008%

    No Known Activations