© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13087
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially those using curly brackets, parenthesis, and common code-related terms

    oai_token-act-pair · gemini-2.0-flash

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    mişti
    -0.52
    bedded
    -0.47
    BorderFactory
    -0.47
     vált
    -0.46
    ureka
    -0.46
     tű
    -0.46
    őle
    -0.46
    வி
    -0.46
    diğini
    -0.45
    ABOR
    -0.45
    POSITIVE LOGITS
    TypedDataSet
    0.77
    StoryboardSegue
    0.76
     estimés
    0.70
    IsInitialized
    0.66
    arakhand
    0.65
     المعيارى
    0.61
     незавершена
    0.60
    FunctionFlags
    0.60
    fromnode
    0.59
     arşivlendi
    0.59
    Activations Density 4.586%

    No Known Activations