© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64233
    Prev
    Next
    INDEX
    Explanations

    process

    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
     মুসলমান
    0.44
    兇
    0.43
     डिफरेंट
    0.42
     ന്
    0.41
     Ledger
    0.40
     frmt
    0.38
     islamic
    0.38
    昧
    0.38
    >[]
    0.37
    स्यों
    0.36
    POSITIVE LOGITS
     process
    0.53
    プロセス
    0.51
     Process
    0.51
    Process
    0.48
     PROCESS
    0.47
    process
    0.45
     procesos
    0.44
    过程
    0.43
     proceso
    0.43
    過程
    0.43
    Activations Density 0.001%

    No Known Activations