© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15824
    Prev
    Next
    INDEX
    Explanations

    a mix of numbers, hyphenated tokens, chemical formulas, identifiers, and lawsuit and election references.

    oai_token-act-pair · gemini-2.0-flash

    Dashes and hyphens

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    IntoConstraints
    -0.80
    Brainz
    -0.79
    djangoproject
    -0.76
    IsContent
    -0.75
    ImageContext
    -0.72
     Италијани
    -0.70
    Jeografia
    -0.70
    SBATCH
    -0.70
    íba
    -0.68
    awtextra
    -0.67
    POSITIVE LOGITS
    -
    1.93
    ‑
    1.01
    ‐
    1.00
    –
    0.91
    -<
    0.85
    -​
    0.83
    -!
    0.81
    -'
    0.81
    -\\
    0.77
    -...
    0.74
    Activations Density 3.906%

    No Known Activations