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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6357
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to politics, especially political parties, elections, and leaders

    oai_token-act-pair · gemini-2.0-flash

    locations

    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
     BoxDecoration
    -0.68
    yntaxException
    -0.62
     InputDecoration
    -0.61
     mergeFrom
    -0.55
     externi
    -0.53
     nahilalakip
    -0.51
     calendriers
    -0.50
    styleUrls
    -0.49
     kasarigan
    -0.49
    σθαι
    -0.49
    POSITIVE LOGITS
     Guatem
    0.64
     Kabul
    0.63
     Peru
    0.63
    المكان
    0.61
    scriptcase
    0.61
     Tuscany
    0.60
    AddWithValue
    0.60
     Persians
    0.58
     Tanzania
    0.58
     Tehran
    0.57
    Activations Density 6.292%

    No Known Activations