© 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. 16167
    Prev
    Next
    INDEX
    Explanations

    gas storage, adsorption, isotherms

    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
     رہنے
    0.44
     وزی
    0.39
     മണിക്ക
    0.38
    㑹
    0.38
    DispatchRequest
    0.38
     ഞാൻ
    0.38
     サイド
    0.38
     വരു
    0.37
    Ꮟ
    0.37
     ವಿಧಾನಸಭಾ
    0.36
    POSITIVE LOGITS
     gas
    0.63
    Gas
    0.59
     adsorption
    0.58
     Gas
    0.57
     desorption
    0.55
     isotherm
    0.54
     isotherms
    0.54
    gas
    0.54
     sorption
    0.50
     LNG
    0.50
    Activations Density 0.020%

    No Known Activations