© 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. 11974
    Prev
    Next
    INDEX
    Explanations

    a mix of code snippets, numbers, and references to Africa

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms and UTF encoding

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

    African or utf

    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
    Datuak
    -1.01
    AndEndTag
    -1.00
    twimg
    -0.97
     дописавши
    -0.90
    OGND
    -0.82
    VIAF
    -0.80
    NameInMap
    -0.79
     صوتيه
    -0.78
    msgTypes
    -0.76
    AnchorStyles
    -0.76
    POSITIVE LOGITS
    kolan
    0.43
    drawSprites
    0.40
     EnglishChoose
    0.39
    графии
    0.37
    griffen
    0.37
    ssan
    0.36
     sva
    0.35
     nak
    0.35
    Honorable
    0.35
     tim
    0.35
    Activations Density 2.611%

    No Known Activations