© 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. 4052
    Prev
    Next
    INDEX
    Explanations

    words related to computer graphics and game design, specifically animation

    oai_token-act-pair · gemini-2.0-flash

    Programming/technical text

    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
    
    -0.85
     مرئيه
    -0.80
    +#+#
    -0.76
     שוליים
    -0.74
    تقاوى
    -0.74
    IsContent
    -0.73
    GraphicsUnit
    -0.73
     onPostExecute
    -0.72
     MessageBoxIcon
    -0.71
    Portale
    -0.67
    POSITIVE LOGITS
    kla
    0.47
     node
    0.44
    node
    0.44
    atra
    0.42
    setAuto
    0.42
     nodo
    0.40
    棄
    0.40
    僻
    0.40
     Seven
    0.40
     composite
    0.40
    Activations Density 1.584%

    No Known Activations