© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6117
    Prev
    Next
    INDEX
    Explanations

    references to magazines or periodical publications

    oai_token-act-pair · gemini-2.0-flash

    publication dates and notable titles

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

    Magazines and publications

    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
     nakalista
    -0.66
    SharedDtor
    -0.66
    kháu
    -0.60
     getIntent
    -0.57
    хьтан
    -0.56
    PMailer
    -0.56
    contentLoaded
    -0.55
     referenties
    -0.55
    queryInterface
    -0.54
     OFDb
    -0.54
    POSITIVE LOGITS
    RenderAtEndOf
    0.63
     May
    0.50
    Bind
    0.46
     arquitectura
    0.46
    damas
    0.45
     Tell
    0.45
     synthesized
    0.45
     október
    0.45
    군
    0.44
     Apr
    0.44
    Activations Density 5.698%

    No Known Activations