© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4807
    Prev
    Next
    INDEX
    Explanations

    technical writing using acronyms

    oai_token-act-pair · gemini-2.0-flash

    business writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Monfieur
    -0.99
     Efq
    -0.94
     itſelf
    -0.93
     Jefus
    -0.88
     Theſe
    -0.88
     myſelf
    -0.86
     iſt
    -0.84
     uſed
    -0.83
     ſever
    -0.81
     Houſe
    -0.81
    POSITIVE LOGITS
    
    0.45
     é
    0.44
     /
    0.44
     га
    0.44
    Addo
    0.44
     '
    0.44
    олові
    0.43
    apos
    0.42
    initComponents
    0.42
     Fra
    0.42
    Activations Density 10.212%

    No Known Activations