© 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. 162
    Prev
    Next
    INDEX
    Explanations

    the industry sectors it is told to find at the start of the document, along with any amperstand-separated words, and some other business wording.

    oai_token-act-pair · gemini-2.0-flash

    tele

    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
    脚注の使い方
    -0.86
    KommentareTeilen
    -0.84
     tartalomajánló
    -0.78
     सत्यापित
    -0.74
    CppMethod
    -0.73
    rawDesc
    -0.72
    expandindo
    -0.72
    ########.
    -0.70
     Lightboxes
    -0.69
     AssemblyVersion
    -0.69
    POSITIVE LOGITS
     tele
    0.79
    tele
    0.70
     Tele
    0.63
    Tele
    0.58
     tel
    0.53
    tel
    0.47
    Tel
    0.46
     Tel
    0.45
     TELE
    0.44
     rád
    0.43
    Activations Density 1.411%

    No Known Activations