© 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. 16346
    Prev
    Next
    INDEX
    Explanations

    technical documentation or discussions related to 3D graphics, animation, and software such as Autodesk Maya and OpenGL

    oai_token-act-pair · gemini-2.0-flash

    technical/programming contexts

    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
     remarqu
    -0.43
    OS
    -0.42
    os
    -0.42
    R
    -0.42
     ketat
    -0.41
     trov
    -0.40
     colère
    -0.40
     blancas
    -0.40
     leçon
    -0.40
     jurado
    -0.39
    POSITIVE LOGITS
    kháu
    0.95
     '\\;'
    0.88
    elemField
    0.85
    AsUp
    0.85
    BeginContext
    0.82
    Personensuche
    0.82
     resourceCulture
    0.82
    IntoConstraints
    0.81
    #+#
    0.80
     useStyles
    0.80
    Activations Density 7.648%

    No Known Activations