© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10812
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially related to game AI or object property handling

    oai_token-act-pair · gemini-2.0-flash

    syntax elements and code structure

    np_token-act-pair-logits · gpt-4o-mini

    )

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     */
    -0.69
    ?></
    -0.59
    */
    -0.57
    XmlSchema
    -0.56
     vapore
    -0.56
    ")]
    -0.55
     ?></
    -0.51
     gioielli
    -0.51
     käns
    -0.50
    ...");
    -0.50
    POSITIVE LOGITS
    ↵
    1.15
    SourceChecksum
    0.79
    脚注の使い方
    0.65
    bootstrapcdn
    0.58
    Cubit
    0.55
    SBATCH
    0.54
     >=",
    0.52
     мәкал
    0.52
     EClass
    0.51
    цездатний
    0.50
    Activations Density 2.508%

    No Known Activations