© 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. 206824
    Prev
    Next
    INDEX
    Explanations

    Al

    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
    受
    1.36
     受
    0.97
    を受
    0.72
    受到
    0.65
     diper
    0.61
    应
    0.60
     rece
    0.56
     应
    0.54
     di
    0.53
    受信
    0.52
    POSITIVE LOGITS
     कारोबार
    0.36
    retail
    0.36
    늄
    0.36
    shaded
    0.36
    昆
    0.36
    kun
    0.35
    Retail
    0.35
    ᵖ
    0.35
    きる
    0.35
    kim
    0.34
    Activations Density 0.001%

    No Known Activations