© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11605
    Prev
    Next
    INDEX
    Explanations

    code snippets, potentially from API or data models, containing variable or property declarations with types like string, double, or DateTimeField.

    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_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    KommentareTeilen
    -0.47
     EClass
    -0.47
    NewLabel
    -0.45
    :✨
    -0.45
    URUS
    -0.42
     khảo
    -0.41
    printStackTrace
    -0.41
    ifrance
    -0.40
    CRIP
    -0.40
    AndroidJUnit
    -0.40
    POSITIVE LOGITS
    TypedDataSet
    0.85
     '\\;'
    0.84
    tagHelperRunner
    0.83
    
    0.64
    bewerken
    0.59
     esternos
    0.59
    nologue
    0.59
    ContentAsync
    0.59
    BeginContext
    0.58
     يتيمه
    0.56
    Activations Density 13.095%

    No Known Activations