© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6222
    Prev
    Next
    INDEX
    Explanations

    conjunctions, prepositions, and articles near words like 'trial,' 'shareholder,' or 'health'.

    oai_token-act-pair · gemini-2.0-flash

    legal advice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     للاسماء
    -1.23
    ThroughAttribute
    -1.20
    :✨
    -1.20
    出版年
    -1.15
     يتيمه
    -1.15
    writeFieldEnd
    -1.14
    Sucesor
    -1.13
    NewUrlParser
    -1.13
    évaluateur
    -1.13
    GOTREF
    -1.10
    POSITIVE LOGITS
     varandra
    0.04
     mères
    0.04
     réguli
    0.02
     démocr
    0.02
     leçons
    0.01
     boî
    0.00
     rayures
    -0.00
     véhicules
    -0.01
     cérami
    -0.01
     prisonniers
    -0.01
    Activations Density 21.940%

    No Known Activations