Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7296
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially those dealing with 3D vectors and rendering meshes

    oai_token-act-pair · gemini-2.0-flash

    vectors and vertexes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     itſelf
    -0.89
     myſelf
    -0.88
     ſeveral
    -0.84
     ſtate
    -0.81
     purpoſe
    -0.73
     Diſ
    -0.72
     greateſt
    -0.72
     Theſe
    -0.72
     Reſ
    -0.71
     iſt
    -0.70
    POSITIVE LOGITS
    <bos>
    0.77
     MainAxisSize
    0.69
     bpy
    0.66
    opengl
    0.65
    Xna
    0.63
    UObject
    0.59
    webgl
    0.59
    gdx
    0.55
    VertexArray
    0.52
    рный
    0.52
    Activations Density 2.483%

    No Known Activations