© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7276
    Prev
    Next
    INDEX
    Explanations

    words related to the activities of international organizations aimed at providing assistance

    oai_token-act-pair · gemini-2.0-flash

    International relations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    MigrationBuilder
    -0.92
     '\\;'
    -0.84
    webElementXpaths
    -0.82
     <>",
    -0.72
    RenderAtEndOf
    -0.71
     فريبيس
    -0.69
    المشاركات
    -0.68
    httphttps
    -0.67
     degradability
    -0.66
    astéro
    -0.65
    POSITIVE LOGITS
     license
    0.41
    ph
    0.40
     scaled
    0.40
    appui
    0.39
     Photocase
    0.39
     насељу
    0.39
     spot
    0.39
    ку
    0.38
    mpe
    0.38
     mainstream
    0.38
    Activations Density 2.412%

    No Known Activations