© 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. 9988
    Prev
    Next
    INDEX
    Explanations

    internet addresses and fragmented sentences with emoticons

    oai_token-act-pair · gemini-2.0-flash

    Mixed content

    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
    afficheront
    -0.47
    PYX
    -0.45
    OrBuilder
    -0.45
    انيف
    -0.45
     ProtoMessage
    -0.43
    officers
    -0.43
    esgue
    -0.42
     Wikispecies
    -0.41
    VersionUID
    -0.41
    NameInMap
    -0.41
    POSITIVE LOGITS
     dovuto
    0.55
     Outros
    0.52
     scolas
    0.48
    rdı
    0.48
    kode
    0.47
    Lihat
    0.47
     Nadie
    0.47
     pronti
    0.46
     orizz
    0.46
    ่อย
    0.46
    Activations Density 18.585%

    No Known Activations