© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87056
    Prev
    Next
    INDEX
    Explanations

    gas prices

    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_23_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
    憚
    0.42
    和平
    0.41
     Asylum
    0.41
     XY
    0.41
     Groundwater
    0.39
     കൃ
    0.39
     Remote
    0.39
     Parse
    0.38
     kon
    0.38
     പറയ
    0.38
    POSITIVE LOGITS
    招
    0.41
    Manu
    0.40
    Datas
    0.37
    minutes
    0.36
    ച്ചത്
    0.35
     ему
    0.35
    手动
    0.35
    加热
    0.35
    abar
    0.35
    ባት
    0.34
    Activations Density 0.001%

    No Known Activations