© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12755
    Prev
    Next
    INDEX
    Explanations

    mathematical or programming code snippets, especially referring to chart dimensions and calculations

    oai_token-act-pair · gemini-2.0-flash

    width related code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ModelSerializer
    -0.66
    躇
    -0.57
    Còn
    -0.55
    ivotopis
    -0.54
    Зноскі
    -0.54
     InputDecoration
    -0.53
     kasarigan
    -0.53
    getSeconds
    -0.52
     CreateTagHelper
    -0.52
    ✨:
    -0.52
    POSITIVE LOGITS
    RegistryLite
    0.57
    rungsseite
    0.51
    MigrationBuilder
    0.50
    <bos>
    0.48
    ://$
    0.47
    fer
    0.47
    okay
    0.46
     дописавши
    0.46
    Datuak
    0.46
    IsContent
    0.46
    Activations Density 4.086%

    No Known Activations