© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7145
    Prev
    Next
    INDEX
    Explanations

    words relating to legal and cause/effect situations, often with specific terminology and legal processes.

    oai_token-act-pair · gemini-2.0-flash

    legal context / orders

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     beginnetje
    -0.54
     chiếm
    -0.53
    خصة
    -0.50
    ʁ
    -0.50
     Corinth
    -0.50
     CORD
    -0.49
    tvguidetime
    -0.48
    embar
    -0.48
    Handlung
    -0.47
    łości
    -0.47
    POSITIVE LOGITS
    bootstrapcdn
    0.84
     متعلقه
    0.81
    <bos>
    0.77
    QMetaType
    0.71
     rospy
    0.67
     distanciation
    0.64
     незавершена
    0.64
    ArrowToggle
    0.63
    XmlAccessType
    0.59
    willReturn
    0.59
    Activations Density 1.575%

    No Known Activations