© 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. 13663
    Prev
    Next
    INDEX
    Explanations

    corporate job titles, especially those including the word "chief."

    oai_token-act-pair · gemini-2.0-flash

    chief

    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
    üksek
    -0.63
     AssemblyCompany
    -0.57
    chement
    -0.54
    Longitud
    -0.53
    frem
    -0.52
    deserved
    -0.52
    Timed
    -0.51
    imensional
    -0.50
    ArgsConstructor
    -0.50
    FieldBuilder
    -0.50
    POSITIVE LOGITS
    neté
    0.51
     resourceCulture
    0.51
    "}";
    0.48
     disambiguazione
    0.47
    wash
    0.47
    RegressionTest
    0.46
    quot
    0.46
     Drapeau
    0.46
    IntoConstraints
    0.46
    ITest
    0.45
    Activations Density 0.869%

    No Known Activations