© 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. 6863
    Prev
    Next
    INDEX
    Explanations

    words related to computer graphics and performance, especially frame rates and visual settings

    oai_token-act-pair · gemini-2.0-flash

    Software and computer performance

    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
    rrggbb
    -0.64
    AndEndTag
    -0.53
    deelte
    -0.52
    AddTagHelper
    -0.50
    existsSync
    -0.49
     inoxydable
    -0.49
     nonUne
    -0.46
    vesse
    -0.46
    aarrggbb
    -0.46
    likon
    -0.45
    POSITIVE LOGITS
    DllImport
    0.56
     ویکی‌آمباردا
    0.55
     المعيارى
    0.53
    IVEREF
    0.53
    fjspx
    0.52
     heaven
    0.52
     sztu
    0.51
    sitis
    0.51
    Phosph
    0.50
    ClientSize
    0.50
    Activations Density 4.937%

    No Known Activations