© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164825
    Prev
    Next
    INDEX
    Explanations

    stomach bleeding and ulcers

    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_31_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
    Neu
    0.37
     Fraction
    0.37
     tet
    0.37
     Fracture
    0.36
     Tet
    0.36
    靘
    0.35
     кабе
    0.35
     brake
    0.35
     बोलो
    0.35
     fracture
    0.34
    POSITIVE LOGITS
    food
    0.42
     food
    0.41
     alimentaire
    0.41
    胃
    0.40
    Food
    0.38
     gastronomy
    0.38
     alimentación
    0.38
     dietary
    0.37
     stomachs
    0.37
     designer
    0.36
    Activations Density 0.005%

    No Known Activations