© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10305
    Prev
    Next
    INDEX
    Explanations

    code documentation or references sections of some kind

    oai_token-act-pair · gemini-2.0-flash

    references and documentation

    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
    <bos>
    -0.54
    //
    -0.50
     Herce
    -0.45
     Профиль
    -0.45
    舺
    -0.42
     admired
    -0.42
    MultipartFile
    -0.42
    WriteLine
    -0.42
     pleaſure
    -0.42
    Сегодня
    -0.42
    POSITIVE LOGITS
     дописавши
    0.83
     resourceCulture
    0.81
    +:+
    0.78
     AssemblyCompany
    0.78
     يتيمه
    0.76
    DOCTYPE
    0.74
     AssemblyProduct
    0.72
    DockStyle
    0.72
    EDEFAULT
    0.71
    SequentialGroup
    0.66
    Activations Density 0.201%

    No Known Activations