© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14522
    Prev
    Next
    INDEX
    Explanations

    failure

    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_15_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
     polytopes
    0.56
     zako
    0.52
    ｎ
    0.51
    𝘆
    0.50
    бую
    0.48
    പം
    0.48
    йн
    0.48
    မီ
    0.47
    ချုပ်
    0.47
     방문
    0.47
    POSITIVE LOGITS
     I
    0.52
     arrhythmia
    0.50
     Synonym
    0.50
     तालुक
    0.48
    进程
    0.46
    糖尿病
    0.45
     Liabilities
    0.44
     сердца
    0.44
    icity
    0.44
     dementia
    0.44
    Activations Density 0.003%

    No Known Activations