© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9779
    Prev
    Next
    INDEX
    Explanations

    sections of code that define repeated fields with names like "String", "Bytes", "Message", and "Enum"

    oai_token-act-pair · gemini-2.0-flash

    repeated

    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
     betweenstory
    -0.58
    bigoplus
    -0.50
    HasBeenSet
    -0.50
     سكانية
    -0.49
    ocats
    -0.48
    ⓧ
    -0.48
    帖最后由
    -0.48
    compressor
    -0.46
    iyle
    -0.45
    Polecam
    -0.45
    POSITIVE LOGITS
    AnchorStyles
    0.83
     متعلقه
    0.58
    getSeconds
    0.55
     Comprometido
    0.54
    <bos>
    0.54
     australiano
    0.50
    subpackage
    0.50
     <=",
    0.50
    apunov
    0.49
    rzost
    0.49
    Activations Density 3.263%

    No Known Activations