© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39775
    Prev
    Next
    INDEX
    Explanations

    cannabis, THC, edibles, terpenes, pack

    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_11_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
     Marijuana
    0.60
    ts
    0.55
     Alcohol
    0.52
    te
    0.50
    药
    0.49
    input
    0.49
     Cannabis
    0.49
     মোত
    0.48
     ال
    0.47
    업
    0.47
    POSITIVE LOGITS
     tenía
    0.52
     zog
    0.52
     așa
    0.49
     agglomer
    0.49
    ње
    0.49
     моби
    0.49
    шлай
    0.48
     assaulting
    0.48
    廉
    0.48
     ühe
    0.47
    Activations Density 0.023%

    No Known Activations