© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5804
    Prev
    Next
    INDEX
    Explanations

    descriptions of hotel interiors with a focus on design or architecture

    oai_token-act-pair · gemini-2.0-flash

    Style adjectives

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    parsedMessage
    -0.85
    WireFormatLite
    -0.79
    Diweddarwch
    -0.75
    tvguidetime
    -0.74
    :✨
    -0.73
     متعلقه
    -0.72
    rungsseite
    -0.69
    Personendaten
    -0.69
    NameInMap
    -0.68
    
    -0.67
    POSITIVE LOGITS
     sophisticated
    0.51
     Scandinavian
    0.50
     statement
    0.50
    COUVER
    0.49
     daring
    0.49
     laid
    0.49
    Soph
    0.49
     minimalist
    0.49
     contemporary
    0.48
     smart
    0.48
    Activations Density 1.216%

    No Known Activations