© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3031
    Prev
    Next
    INDEX
    Explanations

    legal and administrative language mixed with person and location names

    oai_token-act-pair · gemini-2.0-flash

    legal documents, court proceedings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    osom
    -0.47
    mistry
    -0.46
     punt
    -0.45
    !*
    -0.44
    nten
    -0.43
     starost
    -0.43
    時点で
    -0.43
    roben
    -0.42
     middle
    -0.41
     mah
    -0.41
    POSITIVE LOGITS
     kasarigan
    0.87
    DebuggerNonUser
    0.82
    FunctionFlags
    0.78
    Begriffsklä
    0.77
    ConstraintMaker
    0.74
    SourceChecksum
    0.73
    Hauptartikel
    0.72
     autorytatywna
    0.70
     Audiodateien
    0.69
    XmlAccessorType
    0.69
    Activations Density 7.550%

    No Known Activations