© 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. 3659
    Prev
    Next
    INDEX
    Explanations

    Java code related to setting object properties

    oai_token-act-pair · gemini-2.0-flash

    say semicolon

    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
     Mar
    -0.58
    はじめに
    -0.57
    ,
    -0.56
     I
    -0.54
    bel
    -0.53
     Tra
    -0.52
     ‘
    -0.52
     G
    -0.52
    kwds
    -0.51
    )
    -0.50
    POSITIVE LOGITS
     Shakspeare
    0.82
     Efq
    0.75
     BoxFit
    0.74
     Theſe
    0.68
     Voltaire
    0.64
     Beſ
    0.64
     houſe
    0.64
     CGSize
    0.62
     Shaksp
    0.61
     hany
    0.61
    Activations Density 1.365%

    No Known Activations