© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10055
    Prev
    Next
    INDEX
    Explanations

    code snippets with keywords like "node", "descriptor", "operation", "actor", and "selection"

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    — 
    -0.58
    ệng
    -0.54
    PRWEB
    -0.51
    "][
    -0.50
     vuitton
    -0.50
    ziell
    -0.48
    ztály
    -0.48
    progressive
    -0.48
     endwhile
    -0.47
    [...]
    -0.47
    POSITIVE LOGITS
    первых
    0.57
    
    0.56
    曖昧さ回避
    0.54
    évaluateur
    0.52
    complexContent
    0.52
    čník
    0.51
     jadx
    0.49
    AndroidJUnit
    0.49
    DispatchToProps
    0.49
     wireType
    0.48
    Activations Density 0.790%

    No Known Activations