© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50820
    Prev
    Next
    INDEX
    Explanations

    phenylmethyl and Hezbollah

    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_30_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
    оні
    0.37
    reloadData
    0.37
     င
    0.35
    onske
    0.35
    tmpobj
    0.35
    矿
    0.35
    міністра
    0.34
    価格
    0.34
     Pastoral
    0.34
    礦
    0.33
    POSITIVE LOGITS
     येथ
    0.36
     Klang
    0.36
    Lus
    0.35
     robots
    0.34
     Gesundheits
    0.34
     गोवा
    0.34
     Freel
    0.34
     syll
    0.34
     millet
    0.34
     syllabus
    0.34
    Activations Density 0.019%

    No Known Activations