© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7841
    Prev
    Next
    INDEX
    Explanations

    code and code syntax, and related terms like raw data and unsafe memory

    oai_token-act-pair · gemini-2.0-flash

    raw

    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
    ConstraintMaker
    -0.97
    saraba
    -0.94
    IntoConstraints
    -0.86
    horabuena
    -0.85
     MediatR
    -0.84
    exitRule
    -0.83
    yntaxException
    -0.81
    MLLoader
    -0.81
    nextProps
    -0.81
    didSet
    -0.80
    POSITIVE LOGITS
    __
    0.59
    ↵↵
    0.52
    </strong>
    0.51
     sva
    0.51
    </h2>
    0.51
    Alternate
    0.50
    roda
    0.49
    <strong>
    0.48
    7
    0.47
    mada
    0.47
    Activations Density 1.634%

    No Known Activations