© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10390
    Prev
    Next
    INDEX
    Explanations

    snippets of computer code, particularly symbols, names, and text with a Latex-like format

    oai_token-act-pair · gemini-2.0-flash

    Id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    SuppressMessage
    -0.62
    WireFormatLite
    -0.62
    انيف
    -0.57
     comuniques
    -0.52
     незавершена
    -0.50
    ">'.$
    -0.49
    InputTagHelper
    -0.49
    decer
    -0.47
    NSNotification
    -0.47
    tır
    -0.47
    POSITIVE LOGITS
     estimés
    0.68
     AssemblyTitle
    0.65
     الحره
    0.63
    ridae
    0.61
    MinWidth
    0.59
    endphp
    0.58
    </tr>
    0.58
     });
    0.57
     Hotspur
    0.57
     برانيه
    0.57
    Activations Density 3.818%

    No Known Activations