© 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. 11343
    Prev
    Next
    INDEX
    Explanations

    preambles to lists

    oai_token-act-pair · gemini-2.0-flash

    follows

    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
    󠁢
    -0.62
     незавершена
    -0.60
    󠁿
    -0.50
     sientes
    -0.50
     विश्वसनीयता
    -0.49
     giudice
    -0.49
     grij
    -0.49
     estimés
    -0.49
     supérieurs
    -0.48
    Rom
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.72
    GEBURTSDATUM
    0.66
    ніципа
    0.66
    الإنجليزية
    0.65
    MessageOf
    0.63
    urlpatterns
    0.60
     myſelf
    0.59
    PYX
    0.58
    RTEE
    0.57
     protoimpl
    0.57
    Activations Density 1.005%

    No Known Activations