© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4056
    Prev
    Next
    INDEX
    Explanations

    pet food

    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_40_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
     Reich
    0.39
    Rice
    0.39
     '|
    0.38
    indicator
    0.38
     aler
    0.38
     pomen
    0.38
    ujący
    0.37
     formula
    0.37
     eater
    0.37
    PopupMenu
    0.37
    POSITIVE LOGITS
     })();
    0.41
     डेविड
    0.39
     guid
    0.37
    νον
    0.36
    onat
    0.36
    avit
    0.36
     David
    0.35
     complementary
    0.35
     complementarity
    0.35
    ยู
    0.35
    Activations Density 0.015%

    No Known Activations