© 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. 12484
    Prev
    Next
    INDEX
    Explanations

    mentions of scientific publications, German language, and Lithuanian agriculture.

    oai_token-act-pair · gemini-2.0-flash

    Code/documentation

    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
    EndContext
    -0.53
    AMPLE
    -0.52
    EventManager
    -0.45
     Dos
    -0.45
     折
    -0.44
     propo
    -0.41
    PointerException
    -0.41
    Пита
    -0.41
     chefs
    -0.40
     Spurs
    -0.40
    POSITIVE LOGITS
     متعلقه
    0.81
     betweenstory
    0.79
    ArgsConstructor
    0.64
    
    0.61
     AssemblyTitle
    0.61
     Verse
    0.60
    SharedDtor
    0.60
    DoubleQuotes
    0.59
    MIDDLEWARE
    0.59
    SPATH
    0.58
    Activations Density 0.429%

    No Known Activations