© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12925
    Prev
    Next
    INDEX
    Explanations

    articles, possessive pronouns, and adjectives that commonly appear in sports articles

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    PreferredItem
    -0.50
    bev
    -0.39
    wußt
    -0.37
    پر
    -0.36
     fell
    -0.34
     ganglia
    -0.32
    ForRow
    -0.31
    pertise
    -0.31
    ooc
    -0.31
     biri
    -0.31
    POSITIVE LOGITS
    migrationBuilder
    0.84
     continúas
    0.75
     pinulongan
    0.74
    */),
    0.73
     AssemblyCompany
    0.71
    ]=>
    0.71
    "]);
    0.70
    FieldBuilder
    0.68
    RegressionTest
    0.67
    //</
    0.67
    Activations Density 0.504%

    No Known Activations