© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12998
    Prev
    Next
    INDEX
    Explanations

    information about movie credits including the director, actors starring in a film, and other contributors

    oai_token-act-pair · gemini-2.0-flash

    credits of movies/plays

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    LayoutStyle
    -0.48
     di
    -0.44
    qrstuvwxyz
    -0.40
    ники
    -0.39
    ником
    -0.39
    tapi
    -0.38
    IS
    -0.38
    kh
    -0.38
    のと
    -0.38
     w
    -0.37
    POSITIVE LOGITS
    ItemBackground
    1.03
     CreateTagHelper
    1.02
    CloseOperation
    0.88
     iſt
    0.83
     חיצוניים
    0.82
     Monfieur
    0.82
     estekak
    0.82
     Efq
    0.81
     ainfi
    0.81
    RectangleBorder
    0.80
    Activations Density 0.496%

    No Known Activations