© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11206
    Prev
    Next
    INDEX
    Explanations

    words that are commonly used in informal spoken language

    oai_token-act-pair · gemini-2.0-flash

    just

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    just
    -0.73
     just
    -0.73
     Just
    -0.70
     JUST
    -0.68
    JUST
    -0.65
    Just
    -0.63
     justa
    -0.56
     simply
    -0.54
     appena
    -0.49
    simply
    -0.49
    POSITIVE LOGITS
    
    0.82
    帖最后由
    0.68
     communiquez
    0.68
    Décès
    0.66
     protoimpl
    0.66
     oprot
    0.65
    endphp
    0.65
    HideFlags
    0.64
    EndContext
    0.63
    #+#
    0.62
    Activations Density 8.762%

    No Known Activations