© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139823
    Prev
    Next
    INDEX
    Explanations

    wellMethod number used: 1Reason for explanation: MAX_ACTIVATING_TOKENS are all the same token.well

    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_46_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
     avoided
    0.40
     evitando
    0.40
    leases
    0.40
     evit
    0.39
     избе
    0.39
    éviter
    0.39
     arre
    0.38
    噉
    0.38
    vue
    0.37
    ProductImages
    0.37
    POSITIVE LOGITS
    workItem
    0.47
     treball
    0.43
     workable
    0.41
    ชาติ
    0.40
    impression
    0.40
    мне
    0.39
     работой
    0.38
     рабочих
    0.38
    ેશ
    0.37
     bekerja
    0.37
    Activations Density 0.003%

    No Known Activations