© 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. 15879
    Prev
    Next
    INDEX
    Explanations

    sequences of Thai characters within parentheses

    oai_token-act-pair · gemini-2.0-flash

    code-related 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
    ValueStyle
    -0.50
    PageIndex
    -0.47
    cioso
    -0.47
    Palmar
    -0.46
    SequentialGroup
    -0.44
    fromCharCode
    -0.44
     navigu
    -0.44
     made
    -0.44
     vinto
    -0.44
     compter
    -0.43
    POSITIVE LOGITS
    ITHUB
    0.50
    stylers
    0.49
    ISTRATION
    0.46
    aspectj
    0.45
    makeConstraints
    0.44
     CascadeType
    0.44
    xase
    0.44
     Ceramby
    0.43
    upaten
    0.43
    MENAFN
    0.43
    Activations Density 0.102%

    No Known Activations