© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249370
    Prev
    Next
    INDEX
    Explanations

    migration

    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
     ट्रिक
    0.40
    CheckingType
    0.39
    くちゃ
    0.38
    اگ
    0.38
    heet
    0.37
     बेट
    0.37
    ikti
    0.37
    湪
    0.36
    emarks
    0.36
    jours
    0.36
    POSITIVE LOGITS
     mig
    0.59
     migrate
    0.58
     migration
    0.57
     Mig
    0.56
     Migrate
    0.56
     migrated
    0.55
     migratory
    0.55
     Migration
    0.52
    Mig
    0.52
     migrating
    0.50
    Activations Density 0.000%

    No Known Activations