© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6819
    Prev
    Next
    INDEX
    Explanations

    fragments of computer code including date formats, SQL queries, and other programming constructs

    oai_token-act-pair · gemini-2.0-flash

    hyphen separators

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     <<
    -0.84
     =
    -0.82
     ==
    -0.76
     +
    -0.76
     ===
    -0.71
     -,
    -0.71
     —
    -0.70
     >
    -0.70
     ...
    -0.67
     ->
    -0.66
    POSITIVE LOGITS
    --
    1.17
    —
    1.15
    ”—
    0.97
    "--
    0.96
    –
    0.92
    —-
    0.91
    "—
    0.79
    
    0.77
    ---
    0.75
    )—
    0.75
    Activations Density 8.221%

    No Known Activations