© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 3350
    Prev
    Next
    INDEX
    Explanations

    LaTeX math formatting.

    oai_token-act-pair · gemini-2.0-flash

    code delimiters

    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
    ?
    -1.09
    !
    -1.01
    …
    -0.55
    ंदीखरीदारी
    -0.50
    ...
    -0.50
     дописавши
    -0.47
    (
    -0.43
    
    -0.41
     nltk
    -0.41
    RepeatedField
    -0.40
    POSITIVE LOGITS
    ");
    1.33
    ')
    1.23
    ";
    1.23
    ');
    1.20
    ';
    1.16
    ")
    1.12
    `;
    0.92
    /');
    0.90
    */
    0.89
    /')
    0.88
    Activations Density 6.353%

    No Known Activations