© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12887
    Prev
    Next
    INDEX
    Explanations

    place names and words that commonly occur with them

    oai_token-act-pair · gemini-2.0-flash

    Bay

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Bay
    -1.35
    Bay
    -1.34
     bay
    -1.33
     BAY
    -1.31
    bay
    -1.31
    BAY
    -1.27
    ba
    -1.23
    Ba
    -1.20
     Ba
    -1.17
     ba
    -1.12
    POSITIVE LOGITS
    EntityFramework
    0.41
     via
    0.41
    ()];
    0.40
    CODES
    0.38
     مال
    0.38
     match
    0.38
    ようになりました
    0.37
     Who
    0.37
    ทาง
    0.36
    ところは
    0.36
    Activations Density 7.472%

    No Known Activations