© 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. 3153
    Prev
    Next
    INDEX
    Explanations

    legal language related to the success or failure of a legal claim or argument, also sometimes fantasy verbs

    oai_token-act-pair · gemini-2.0-flash

    legal claims/statements

    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
    RegistryLite
    -0.79
    oredCriteria
    -0.77
     MyBatis
    -0.75
    webElementXpaths
    -0.74
    migrationBuilder
    -0.69
    addCriterion
    -0.68
     <=",
    -0.68
    EDEFAULT
    -0.68
     محفوظة
    -0.66
    memoized
    -0.66
    POSITIVE LOGITS
     initComponents
    0.50
    retum
    0.47
     onStart
    0.46
     kohdetta
    0.43
     Sall
    0.42
     Roskov
    0.41
    aso
    0.41
    วย
    0.41
     start
    0.41
     referenties
    0.41
    Activations Density 1.196%

    No Known Activations