© 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. 20596
    Prev
    Next
    INDEX
    Explanations

    to use

    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
    เพื่อน
    0.50
     pour
    0.41
     ped
    0.41
    đ
    0.40
     เพ
    0.39
     për
    0.39
     för
    0.38
     pentru
    0.38
    fusion
    0.38
     para
    0.37
    POSITIVE LOGITS
    以
    2.42
     以
    2.05
    是以
    1.07
    ด้วย
    1.05
    以為
    0.93
    以为
    0.89
    以此
    0.82
     yǐ
    0.79
     ด้วย
    0.76
    以降
    0.76
    Activations Density 0.006%

    No Known Activations