© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 615
    Prev
    Next
    INDEX
    Explanations

    the context of animation and photography, particularly animation techniques with cameras

    oai_token-act-pair · gemini-2.0-flash

    frames

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    
    -0.52
     Mas
    -0.48
     mon
    -0.47
     gad
    -0.45
    BagLayout
    -0.43
    loch
    -0.43
    uña
    -0.43
    ServletContext
    -0.42
    river
    -0.42
    mbals
    -0.41
    POSITIVE LOGITS
     frames
    1.22
     Frames
    1.18
     frame
    1.18
     Frame
    1.08
     animation
    1.07
    frames
    1.04
    frame
    0.99
     FRAME
    0.98
     animated
    0.97
    Frames
    0.95
    Activations Density 1.472%

    No Known Activations