© 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. 15838
    Prev
    Next
    INDEX
    Explanations

    symbols, variable names and other fragments of code or mathematical expressions within text

    oai_token-act-pair · gemini-2.0-flash

    say "H" words

    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
    出版年
    -0.66
    
    -0.63
    BagConstraints
    -0.61
    astify
    -0.53
    TestingModule
    -0.52
    ollectionView
    -0.50
    twimg
    -0.49
    WebVitals
    -0.49
    adaptiveStyles
    -0.48
    Datuak
    -0.48
    POSITIVE LOGITS
     HB
    1.20
     HC
    1.20
     HF
    1.16
     HM
    1.13
     HH
    1.13
     HP
    1.12
     HV
    1.11
     HCC
    1.10
     HT
    1.09
    HC
    1.09
    Activations Density 8.670%

    No Known Activations