© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9525
    Prev
    Next
    INDEX
    Explanations

    references to historical events and historical figures as well as dates.

    oai_token-act-pair · gemini-2.0-flash

    coding or programming-related terms

    np_token-act-pair-logits · gpt-4o-mini

    Technical or old texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    indale
    -0.52
     quelcon
    -0.48
    IGENCE
    -0.46
    Defined
    -0.46
    asztal
    -0.46
     Desen
    -0.46
     enfrentan
    -0.46
     zod
    -0.45
    tileno
    -0.45
    endam
    -0.44
    POSITIVE LOGITS
     HttpNotFound
    0.63
    WireFormatLite
    0.62
    انيف
    0.54
     للاسماء
    0.53
    AndroidJUnit
    0.52
    NullCheck
    0.50
     mergeFrom
    0.50
    CPtr
    0.49
     JpaRepository
    0.49
    probleme
    0.49
    Activations Density 1.038%

    No Known Activations