© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9357
    Prev
    Next
    INDEX
    Explanations

    information about film production, including directors, writers, and production staff

    oai_token-act-pair · gemini-2.0-flash

    directing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     director
    -0.89
     Director
    -0.81
    Director
    -0.80
    director
    -0.75
     directors
    -0.73
     DIRECTOR
    -0.67
    Directors
    -0.67
     directed
    -0.67
    Directed
    -0.66
     Directors
    -0.63
    POSITIVE LOGITS
    تقاوى
    0.94
    ValueStyle
    0.82
    IVEREF
    0.81
    tagHelperRunner
    0.80
    ImageContext
    0.73
    ########.
    0.73
     AssemblyCulture
    0.69
     beginnetje
    0.69
    IntoConstraints
    0.69
     INTERESAR
    0.68
    Activations Density 2.091%

    No Known Activations