© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13541
    Prev
    Next
    INDEX
    Explanations

    words related to events like festivals, ceremonies, sports and crime, with a tendency to activate more strongly for items in a list or description of a sequence of events.

    oai_token-act-pair · gemini-2.0-flash

    News articles

    np_max-act-logits · gemini-2.0-flash

    archaic spellings

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     
    -0.81
    .
    -0.71
     (
    -0.64
      
    -0.63
    -
    -0.63
    ,
    -0.62
    ↵↵
    -0.60
    ...
    -0.59
    ↵
    -0.59
    …
    -0.55
    POSITIVE LOGITS
     itſelf
    1.97
     Monfieur
    1.95
     myſelf
    1.93
     ―――――
    1.85
     فريبيس
    1.84
    DockStyle
    1.83
     autorytatywna
    1.80
     Theſe
    1.78
     незавершена
    1.78
     AssemblyCulture
    1.78
    Activations Density 51.001%

    No Known Activations