© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 124256
    Prev
    Next
    INDEX
    Explanations

    oils and carrier oils

    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_37_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
     Schein
    0.42
     谢
    0.40
    Sche
    0.39
     bug
    0.39
    padă
    0.39
    Bug
    0.37
     ек
    0.37
    леду
    0.36
     राजप
    0.36
    рово
    0.36
    POSITIVE LOGITS
     castor
    0.48
    蓖
    0.47
     Vegetable
    0.46
     Cast
    0.46
     vegetable
    0.44
     blackened
    0.42
     கரி
    0.41
     वेजिट
    0.39
     grap
    0.38
    Cast
    0.38
    Activations Density 0.028%

    No Known Activations