© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10922
    Prev
    Next
    INDEX
    Explanations

    foreign-sounding names or words

    oai_token-act-pair · gemini-2.0-flash

    multiple languages

    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
     close
    -0.50
     des
    -0.46
     the
    -0.46
    ↵
    -0.45
     as
    -0.45
     support
    -0.45
     initial
    -0.45
     
    -0.44
     in
    -0.44
     mis
    -0.44
    POSITIVE LOGITS
     Theſe
    1.07
     Monfieur
    1.06
     myſelf
    1.02
     mergeFrom
    1.01
    GEBURTSDATUM
    1.00
    MemoryWarning
    0.94
     itſelf
    0.94
     pleaſure
    0.92
     whoſe
    0.90
     Roskov
    0.90
    Activations Density 1.056%

    No Known Activations