© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 176671
    Prev
    Next
    INDEX
    Explanations

    Fill

    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_50_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
    迳
    0.45
    断面
    0.41
    gateTime
    0.40
    কলার
    0.40
    वरी
    0.39
     saque
    0.39
     Nucleaires
    0.39
     भारतातील
    0.39
    搽
    0.38
    ленные
    0.38
    POSITIVE LOGITS
    ᾖ
    0.39
    alk
    0.38
     மி
    0.38
     sure
    0.37
    ixel
    0.37
    unit
    0.37
    sure
    0.36
    UIT
    0.36
     मित
    0.36
    buffalo
    0.35
    Activations Density 0.000%

    No Known Activations