© 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. 10071
    Prev
    Next
    INDEX
    Explanations

    technical writing containing numbers and coordinates

    oai_token-act-pair · gemini-2.0-flash

    Number 4

    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
    rawDesc
    -0.54
    PLICIT
    -0.46
    kundige
    -0.46
    reggio
    -0.44
    ône
    -0.43
     sc
    -0.43
    Granada
    -0.42
     aceptas
    -0.42
    ниц
    -0.42
    wendungen
    -0.42
    POSITIVE LOGITS
    ArgsConstructor
    0.84
    TagMode
    0.81
    Datuak
    0.75
    DotNetBar
    0.75
    ValueStyle
    0.75
     referrerpolicy
    0.74
    ImageContext
    0.72
    AddTagHelper
    0.72
    bootstrapcdn
    0.71
    Hentet
    0.70
    Activations Density 0.901%

    No Known Activations