© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16200
    Prev
    Next
    INDEX
    Explanations

    words relating to the political conflict between Denmark and Germany in the 1800s

    oai_token-act-pair · gemini-2.0-flash

    Political agreements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    expandindo
    -0.73
    MLLoader
    -0.69
    éroport
    -0.56
    WebpackPlugin
    -0.55
     Савезне
    -0.53
    providedIn
    -0.50
     randomness
    -0.50
    StoryboardSegue
    -0.49
    bitat
    -0.49
    SequentialGroup
    -0.48
    POSITIVE LOGITS
     autorytatywna
    0.54
     ad
    0.49
    ious
    0.49
    SharedCtor
    0.48
     raiſ
    0.48
    Asia
    0.48
    ADJ
    0.47
     postIndex
    0.47
     Asia
    0.47
    WritableDatabase
    0.46
    Activations Density 3.189%

    No Known Activations