© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10864
    Prev
    Next
    INDEX
    Explanations

    code-related terms and syntax such as `V`, `cs`, `es`, `package`, `filter`, `fun`, `val`, `return`.

    oai_token-act-pair · gemini-2.0-flash

    computer programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     تضيفلها
    -0.99
    GEBURTSDATUM
    -0.94
     transfieras
    -0.93
     estekak
    -0.91
     صوتيه
    -0.91
    Personendaten
    -0.90
    LookAnd
    -0.89
     AssemblyCulture
    -0.89
    хьтан
    -0.88
    Datuak
    -0.87
    POSITIVE LOGITS
    <bos>
    0.49
    se
    0.44
     cubos
    0.42
     -
    0.41
    }-\
    0.40
    |+
    0.40
    In
    0.40
    λι
    0.40
    .
    0.39
    :
    0.38
    Activations Density 12.942%

    No Known Activations