© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 123818
    Prev
    Next
    INDEX
    Explanations

    pickled cucumbers, pickles, pickled sport peppers

    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
    UID
    0.40
    mailbox
    0.40
     crown
    0.39
     Gerber
    0.39
    uited
    0.39
     chiefs
    0.38
     Υ
    0.37
    Watcher
    0.37
     Pil
    0.36
     mailbox
    0.36
    POSITIVE LOGITS
     fly
    0.39
     shredded
    0.38
     rested
    0.37
     مات
    0.37
    แม
    0.37
     effort
    0.36
    馬
    0.36
     விர
    0.35
     disposición
    0.35
     resting
    0.34
    Activations Density 0.001%

    No Known Activations