© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5361
    Prev
    Next
    INDEX
    Explanations

    HTML span tags with a style attribute

    oai_token-act-pair · gemini-2.0-flash

    span

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     complete
    -0.59
    はずです
    -0.58
    AMIN
    -0.58
    ようになります
    -0.57
     mano
    -0.54
    hil
    -0.54
    ÁB
    -0.52
     vel
    -0.52
     important
    -0.52
     ré
    -0.52
    POSITIVE LOGITS
     Athenians
    0.83
    riwal
    0.80
     Bourgoin
    0.75
    Havolalar
    0.74
     tartalomajánló
    0.73
    modb
    0.72
     Tasman
    0.72
    fastjson
    0.70
     gundam
    0.69
    abstractmethod
    0.69
    Activations Density 0.213%

    No Known Activations