© 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. 14900
    Prev
    Next
    INDEX
    Explanations

    legal language related to contracts and warranties

    oai_token-act-pair · gemini-2.0-flash

    terms related to contracts and drafting

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

    drafting

    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
    <_
    -0.47
    Geographie
    -0.46
     opérés
    -0.45
    ケート
    -0.44
    cèse
    -0.43
    etje
    -0.43
     aidant
    -0.43
    コード
    -0.42
     فريبيس
    -0.41
    CppMethod
    -0.40
    POSITIVE LOGITS
     drafting
    0.85
     drafts
    0.83
     Drafting
    0.82
     draft
    0.80
     drafted
    0.76
    draft
    0.73
     DRAFT
    0.73
    rafted
    0.70
     dra
    0.70
    fine
    0.70
    Activations Density 4.933%

    No Known Activations