© 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-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5030
    Prev
    Next
    INDEX
    Explanations

    named entities and other proper nouns

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    oredCriteria
    -0.59
     acontecimientos
    -0.54
    منابع
    -0.53
     surla
    -0.53
     PLASTIC
    -0.52
     πό
    -0.52
     Drawing
    -0.51
    ఔ
    -0.50
     Cows
    -0.49
     Ereignisse
    -0.49
    POSITIVE LOGITS
     cost
    1.41
     Cost
    1.41
    Cost
    1.38
    cost
    1.33
     costing
    1.25
     COST
    1.23
    COST
    1.16
     costs
    1.00
     Costs
    0.95
     Coast
    0.93
    Activations Density 0.364%

    No Known Activations