© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2242
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with the entertainment industry, specifically relating to movies, awards, and people's careers.

    oai_token-act-pair · gemini-2.0-flash

    entertainment breakthrough/recognition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    <bos>
    -0.96
    RegressionTest
    -0.65
     Drapeau
    -0.63
    StructEnd
    -0.60
    toFloat
    -0.59
    berly
    -0.56
    ChildIndex
    -0.55
    IDAD
    -0.54
     AspNetCore
    -0.53
    =""/>
    -0.53
    POSITIVE LOGITS
    Jeografia
    0.56
     ThemeData
    0.49
    getDoctrine
    0.47
     Emerging
    0.46
    PageRoute
    0.46
    yargs
    0.45
     emerging
    0.44
    eseorang
    0.44
    abestanden
    0.43
     demographic
    0.42
    Activations Density 0.625%

    No Known Activations