© 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. 4991
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to a variety of technical and specialized topics

    oai_token-act-pair · gemini-2.0-flash

    foreign language or specialized terms

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

    technical/academic documents

    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
     
    -0.79
    ,
    -0.73
    <unused60>
    -0.64
    1
    -0.63
    <unused61>
    -0.63
     I
    -0.59
    <unused63>
    -0.58
     F
    -0.58
    <unused62>
    -0.57
     in
    -0.57
    POSITIVE LOGITS
     ویکی‌آمباردا
    1.28
    featureID
    1.20
     Theſe
    1.16
    writeFieldEnd
    1.16
     متعلقه
    1.10
     Мексичка
    1.10
     للاسماء
    1.10
     виправивши
    1.09
     ModelExpression
    1.07
    OGND
    1.06
    Activations Density 6.025%

    No Known Activations