© 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. 250742
    Prev
    Next
    INDEX
    Explanations

    sw words

    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
    卄
    0.41
    ulla
    0.40
    iumi
    0.39
    ії
    0.38
     کھل
    0.38
    স্ত্রী
    0.38
    ippings
    0.38
    ربة
    0.38
    üre
    0.37
    чених
    0.37
    POSITIVE LOGITS
     sw
    0.72
     Sw
    0.70
    Sw
    0.66
    sw
    0.60
     b
    0.56
     swarm
    0.52
     Swal
    0.47
    <0x99>
    0.46
     сва
    0.46
     swipes
    0.46
    Activations Density 0.001%

    No Known Activations