© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12030
    Prev
    Next
    INDEX
    Explanations

    program code snippets

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
    <bos>
    -0.52
     VIDEOTAPE
    -0.50
    complexContent
    -0.46
    XMLSchema
    -0.45
    +:+
    -0.45
    发表于
    -0.43
     odkazy
    -0.42
     상세
    -0.42
    ########.
    -0.42
     Walkover
    -0.42
    POSITIVE LOGITS
    //
    0.31
    BindView
    0.26
    [toxicity=0]
    0.25
     Jefus
    0.24
    <h1>
    0.24
    konomi
    0.23
    anueva
    0.23
     بيها
    0.23
     Nacionales
    0.23
    <h2>
    0.22
    Activations Density 5.334%

    No Known Activations