© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20501
    Prev
    Next
    INDEX
    Explanations

    colors

    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
     對
    0.58
     đối
    0.55
    对
    0.54
     against
    0.51
    against
    0.51
    對
    0.48
     Against
    0.47
    Against
    0.46
     对
    0.45
     Đối
    0.45
    POSITIVE LOGITS
    Tie
    0.39
    厙
    0.39
    颜色
    0.38
    绝对
    0.37
    䢁
    0.36
     diferenci
    0.35
    先
    0.35
    ాల్సి
    0.34
    传
    0.34
    色
    0.33
    Activations Density 0.002%

    No Known Activations