© 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. 51345
    Prev
    Next
    INDEX
    Explanations

    formal religious figures and attire

    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
    ×</
    0.39
     patients
    0.38
    udes
    0.38
     fencing
    0.37
    患者
    0.37
     vliegtuig
    0.37
    announced
    0.36
     lieux
    0.36
     advertised
    0.35
     screenings
    0.35
    POSITIVE LOGITS
    target
    0.42
     evergreen
    0.38
    Ը
    0.36
    onion
    0.35
    䄳
    0.35
     prototyping
    0.34
     order
    0.34
    ਧ
    0.34
     syn
    0.34
     cDNA
    0.34
    Activations Density 0.005%

    No Known Activations