© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6144
    Prev
    Next
    INDEX
    Explanations

    chunks of source code, math formulas, and other structured text.

    oai_token-act-pair · gemini-2.0-flash

    academic/technical writing

    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
    ...-
    -0.72
    __;
    -0.70
     (...
    -0.68
    </strong>
    -0.67
     CanadaChoose
    -0.67
    :...
    -0.67
    =*
    -0.65
     surla
    -0.64
     BaseActivity
    -0.63
    .../
    -0.63
    POSITIVE LOGITS
    <bos>
    1.13
    InjectAttribute
    0.70
    OGND
    0.69
     Monfieur
    0.65
    ↵
    0.64
     itſelf
    0.59
    IsContent
    0.58
     typelib
    0.57
     purpoſe
    0.57
     Normdatei
    0.56
    Activations Density 43.015%

    No Known Activations