© 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. 136861
    Prev
    Next
    INDEX
    Explanations

    exhaust back pressure

    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
     সঙ্গী
    0.41
     zip
    0.39
    ([...
    0.38
     alt
    0.37
    Alt
    0.36
     Trinidad
    0.36
     vagina
    0.36
    攜
    0.36
     venture
    0.36
    Tur
    0.35
    POSITIVE LOGITS
    back
    0.71
    Back
    0.69
     back
    0.65
    BACK
    0.63
     BACK
    0.62
     Back
    0.61
    बैक
    0.58
     बैक
    0.57
     hydrostatic
    0.54
    バック
    0.51
    Activations Density 0.001%

    No Known Activations