© 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. 12501
    Prev
    Next
    INDEX
    Explanations

    disjointed groupings of words relating to futuristic things, technology, and finance.

    oai_token-act-pair · 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
     pandemic
    -1.12
     COVID
    -1.09
     covid
    -1.06
    COVID
    -1.02
    pandemic
    -1.01
     Covid
    -1.00
     pandemi
    -0.98
     Pandemie
    -0.98
    Covid
    -0.94
     pandemia
    -0.94
    POSITIVE LOGITS
     idéia
    0.71
     xrange
    0.70
    onomía
    0.63
     svn
    0.56
     http
    0.49
    http
    0.49
    Swag
    0.47
    svn
    0.46
    Références
    0.44
    loit
    0.44
    Activations Density 0.076%

    No Known Activations