© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12159
    Prev
    Next
    INDEX
    Explanations

    HTML list elements such as `<li>` and `<ul>`.

    oai_token-act-pair · gemini-2.0-flash

    say "li" word

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Li
    -1.69
     li
    -1.60
    Li
    -1.57
     LI
    -1.52
     Lib
    -1.40
     LIP
    -1.33
     Lipp
    -1.32
     LIS
    -1.31
     LIB
    -1.30
     Ly
    -1.29
    POSITIVE LOGITS
     Esau
    0.59
     Schot
    0.51
    HomeAsUpEnabled
    0.49
     peindre
    0.47
    undert
    0.44
     Cerr
    0.44
    zusch
    0.44
    ecraft
    0.42
    Opaque
    0.41
     Kette
    0.40
    Activations Density 0.821%

    No Known Activations