© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205431
    Prev
    Next
    INDEX
    Explanations

    sample

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     terhadap
    0.40
     precum
    0.39
     Hạ
    0.39
    下
    0.38
     hạ
    0.38
     concerning
    0.38
     sonra
    0.38
     altında
    0.38
    kün
    0.38
    kowe
    0.38
    POSITIVE LOGITS
     sample
    0.59
     SAMPLE
    0.58
    样本
    0.55
    sample
    0.52
     नमू
    0.52
     샘
    0.52
     samples
    0.50
    SAMPLE
    0.49
    サンプル
    0.49
     amost
    0.48
    Activations Density 0.000%

    No Known Activations