© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5520
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "as" in legal/financial contexts

    oai_token-act-pair · gemini-2.0-flash

    as

    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
     NSCoder
    -0.71
    routeProvider
    -0.69
    
    -0.68
     InputDecoration
    -0.67
    octanol
    -0.65
    |}{$
    -0.65
    PyExc
    -0.63
     AssemblyCompany
    -0.62
    OrBuilder
    -0.60
     BoxDecoration
    -0.59
    POSITIVE LOGITS
     reflected
    0.49
     Tại
    0.47
     Cheek
    0.46
    ://
    0.45
    mach
    0.44
     also
    0.44
     certified
    0.43
     Alembic
    0.43
     بيها
    0.43
     qualified
    0.42
    Activations Density 2.332%

    No Known Activations