© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14259
    Prev
    Next
    INDEX
    Explanations

    words indicating status and acceptance, or actions related to them

    oai_token-act-pair · gemini-2.0-flash

    the word "as" in multiple languages

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

    marked

    np_max-act-logits · gemini-2.0-flash

    recognize

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    thenia
    -0.62
    بوابة
    -0.59
     AssemblyCompany
    -0.56
    ifrance
    -0.56
    SourceChecksum
    -0.54
     disambiguazione
    -0.53
    曖昧さ回避
    -0.53
    
    -0.50
    "}"
    -0.48
     kaarangay
    -0.47
    POSITIVE LOGITS
     as
    2.23
     sebagai
    1.32
    為
    1.23
    为
    1.21
    as
    1.12
     ως
    1.10
     jako
    1.07
     как
    1.06
     як
    1.06
    sebagai
    1.05
    Activations Density 2.342%

    No Known Activations