© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7737
    Prev
    Next
    INDEX
    Explanations

    capitalized names of countries, people, organizations as well as places and titles

    oai_token-act-pair · gemini-2.0-flash

    Foreign language fragments

    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
     pleaſure
    -1.71
     Majefty
    -1.64
     purpoſe
    -1.61
     Monfieur
    -1.56
     Anſ
    -1.56
     Jefus
    -1.55
     houſe
    -1.54
     raiſ
    -1.53
     Efq
    -1.50
     myſelf
    -1.47
    POSITIVE LOGITS
     kon
    0.65
     d
    0.65
     les
    0.63
    �
    0.59
     k
    0.54
     Mat
    0.53
     Mer
    0.52
     mer
    0.52
     ze
    0.51
     hö
    0.50
    Activations Density 6.472%

    No Known Activations