© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6838
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with linear equations and functions in a mathematical or technical context

    oai_token-act-pair · gemini-2.0-flash

    terms related to linear functions and approximations

    np_token-act-pair-logits · gpt-4o-mini

    linear

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     يتيمه
    -0.90
    ArgsConstructor
    -0.87
    Демографія
    -0.77
    thâu
    -0.77
     ModelExpression
    -0.75
     fiscale
    -0.72
     المعيارى
    -0.68
    Rüyada
    -0.67
     itſelf
    -0.67
    WebVitals
    -0.66
    POSITIVE LOGITS
     ma
    0.59
    ="@+
    0.57
     function
    0.54
     ad
    0.53
     Ma
    0.52
     di
    0.52
    ,
    0.50
     tr
    0.49
     B
    0.49
     dis
    0.48
    Activations Density 4.005%

    No Known Activations