© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14682
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas, symbols and expressions

    oai_token-act-pair · gemini-2.0-flash

    Math/code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     propOrder
    -0.90
    <bos>
    -0.85
    Jeografia
    -0.79
     CreateTagHelper
    -0.79
    ']],
    -0.77
    )))));
    -0.70
    ValueStyle
    -0.68
    ']=
    -0.68
    BeginContext
    -0.67
     StatefulWidget
    -0.67
    POSITIVE LOGITS
    ExecuteReader
    0.56
    heça
    0.48
     취
    0.44
    gridad
    0.44
    ingan
    0.43
     око
    0.41
    getStringExtra
    0.41
    URLException
    0.41
     мной
    0.41
     MotionEvent
    0.40
    Activations Density 6.454%

    No Known Activations