© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11171
    Prev
    Next
    INDEX
    Explanations

    words related to food, recreational activities, and personal connections or opinions.

    oai_token-act-pair · gemini-2.0-flash

    Argumentative blog comments

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.57
    LayoutPanel
    -0.57
    agli
    -0.54
    xnn
    -0.53
    Portale
    -0.50
    fromCharCode
    -0.50
    MigrationBuilder
    -0.49
    thodon
    -0.48
    __.__
    -0.48
    ικά
    -0.47
    POSITIVE LOGITS
    
    0.70
     通販
    0.57
     ways
    0.55
    GeoNames
    0.52
     getItemId
    0.52
     Wikimédia
    0.51
    contentLoaded
    0.50
    İstinadlar
    0.48
     Ways
    0.47
    fixing
    0.47
    Activations Density 2.922%

    No Known Activations