© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10782
    Prev
    Next
    INDEX
    Explanations

    language and phrasing commonly found in scientific papers

    oai_token-act-pair · gemini-2.0-flash

    we

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     my
    -1.96
     myself
    -1.80
     mijn
    -1.52
     I
    -1.50
    my
    -1.49
     meines
    -1.48
     meiner
    -1.42
     моих
    -1.42
     моего
    -1.41
     мои
    -1.41
    POSITIVE LOGITS
     we
    1.52
    We
    1.26
     We
    1.23
     nous
    1.13
    我们
    1.08
    我們
    1.07
     мы
    1.05
     ourselves
    1.05
    我们是
    1.05
     我们
    1.02
    Activations Density 5.510%

    No Known Activations