© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7246
    Prev
    Next
    INDEX
    Explanations

    technical production aspects of film and TV.

    oai_token-act-pair · gemini-2.0-flash

    film and camera

    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
    Negative Logits
     resourceCulture
    -0.81
     AssemblyProduct
    -0.73
    RetentionPolicy
    -0.61
    GeoNames
    -0.61
    libft
    -0.59
    principalTable
    -0.52
     keş
    -0.50
    hasMoreElements
    -0.50
     FormsModule
    -0.50
    DropTable
    -0.48
    POSITIVE LOGITS
    ExecuteReader
    0.60
    ypal
    0.55
     BoxFit
    0.52
    riedenheit
    0.52
     ujednoznacz
    0.51
     longue
    0.51
    ConstraintMaker
    0.51
    }}]{
    0.49
    Nhưng
    0.49
     Acton
    0.49
    Activations Density 2.039%

    No Known Activations