© 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. 13854
    Prev
    Next
    INDEX
    Explanations

    words related to history, politics, and cultural groups, especially in the context of Germany and Denmark.

    oai_token-act-pair · gemini-2.0-flash

    Historical events

    np_max-act-logits · gemini-2.0-flash
    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
     مشين
    -0.56
     dubbio
    -0.50
     chiave
    -0.50
    рс
    -0.50
    Sucesor
    -0.50
     complètes
    -0.50
     HasFactory
    -0.49
     médicaux
    -0.49
     correctes
    -0.48
    Hauptartikel
    -0.48
    POSITIVE LOGITS
    TypedDataSet
    0.68
    ArrowToggle
    0.61
    bootstrapcdn
    0.59
    SpringBootTest
    0.57
    IMPORTED
    0.57
    ereq
    0.56
     Eff
    0.54
    bary
    0.54
    esterday
    0.52
     QName
    0.51
    Activations Density 7.080%

    No Known Activations