© 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. 4701
    Prev
    Next
    INDEX
    Explanations

    a diverse set of proper nouns and keywords related to business, law and dates.

    oai_token-act-pair · gemini-2.0-flash

    legal and case-related terms

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

    legal/business language

    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
     ProtoMessage
    -0.74
    脚注の使い方
    -0.74
    IntoConstraints
    -0.63
    AnchorStyles
    -0.62
    ]=>
    -0.57
     initComponents
    -0.55
    HandlerContext
    -0.54
     שוליים
    -0.53
    ofern
    -0.53
    Einzelnachweise
    -0.52
    POSITIVE LOGITS
     on
    0.50
    ddots
    0.45
    <bos>
    0.44
    chyma
    0.44
    ]--;
    0.43
    abbix
    0.43
    hikari
    0.43
     On
    0.42
     Object
    0.41
    siella
    0.41
    Activations Density 1.170%

    No Known Activations