© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6895
    Prev
    Next
    INDEX
    Explanations

    the possessive form of "agency."

    oai_token-act-pair · gemini-2.0-flash

    intelligence operations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    
    -0.71
    تقاوى
    -0.62
    ंदीखरीदारी
    -0.59
     насељу
    -0.58
     EconPapers
    -0.55
    发表于
    -0.54
     AssemblyCulture
    -0.54
    μαστε
    -0.53
    ikkert
    -0.53
     initComponents
    -0.53
    POSITIVE LOGITS
     judiciales
    0.51
     فريبيس
    0.50
     varandra
    0.50
     ferroviaire
    0.45
    BufferException
    0.44
     negozi
    0.43
    withIdentifier
    0.42
    jsoup
    0.42
     interesa
    0.42
     necesariamente
    0.42
    Activations Density 2.184%

    No Known Activations