© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12953
    Prev
    Next
    INDEX
    Explanations

    C code snippets that include data structures and macros related to memory access and hardware initialization.

    oai_token-act-pair · gemini-2.0-flash

    struct

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ")));
    -0.75
     kaarangay
    -0.67
    ')")
    -0.67
     $_"
    -0.67
     Hift
    -0.65
    évaluateur
    -0.65
    )++;
    -0.65
     Infórmanos
    -0.64
    )");
    -0.64
     ExecuteAsync
    -0.63
    POSITIVE LOGITS
    dsi
    0.54
    drm
    0.53
     kubernetes
    0.53
    dma
    0.51
    pdev
    0.51
     jPanel
    0.50
    estinian
    0.49
     ssd
    0.49
    vmware
    0.49
    rte
    0.48
    Activations Density 14.922%

    No Known Activations