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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10130
    Prev
    Next
    INDEX
    Explanations

    terms related to business finance and competition

    oai_token-act-pair · gemini-2.0-flash

    unusual letter combinations

    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
    oredCriteria
    -0.87
    Autoritní
    -0.78
    CardBody
    -0.69
    DoubleQuotes
    -0.68
    SourceChecksum
    -0.68
     OFDb
    -0.67
    новниш
    -0.67
    InitVars
    -0.66
    ChildScrollView
    -0.64
    astéroïdes
    -0.63
    POSITIVE LOGITS
     il
    0.49
    ilon
    0.47
    gls
    0.43
     ổn
    0.43
     Cyc
    0.42
     mắc
    0.39
     bev
    0.38
     inelastic
    0.37
    CrossRef
    0.37
     ultra
    0.37
    Activations Density 1.461%

    No Known Activations