© 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. 13348
    Prev
    Next
    INDEX
    Explanations

    a variety of keywords from news headlines, scientific papers, and technology articles.

    oai_token-act-pair · gemini-2.0-flash

    prepositions

    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
     Mga
    -0.44
    --)
    -0.43
    Existen
    -0.40
    NUMX
    -0.39
     незавершена
    -0.38
     $_"
    -0.38
     ""],
    -0.38
     configureStore
    -0.38
    Acest
    -0.37
     Demp
    -0.35
    POSITIVE LOGITS
     From
    1.63
     With
    1.63
     By
    1.46
     Through
    1.46
     Between
    1.37
     Without
    1.35
    From
    1.34
     Within
    1.32
    With
    1.32
     Against
    1.30
    Activations Density 11.417%

    No Known Activations