© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6072
    Prev
    Next
    INDEX
    Explanations

    references to legal acts, sections, and government organizations

    oai_token-act-pair · gemini-2.0-flash

    Act

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     continúas
    -0.69
    Portály
    -0.62
    Rüyada
    -0.59
    djangoproject
    -0.57
     تانيه
    -0.56
     Mère
    -0.54
    httphttps
    -0.54
     wireType
    -0.53
     referrerpolicy
    -0.53
    Diweddarwch
    -0.52
    POSITIVE LOGITS
    
    0.50
    calyp
    0.50
    oustics
    0.50
    Chamber
    0.49
    loroethene
    0.48
    SBATCH
    0.47
    pezi
    0.47
    ArgsConstructor
    0.47
    ilibr
    0.47
     Barclay
    0.47
    Activations Density 2.129%

    No Known Activations