© 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. 8173
    Prev
    Next
    INDEX
    Explanations

    numbers, especially years

    oai_token-act-pair · gemini-2.0-flash

    tokens or symbols related to identifiers or codes

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

    numbers

    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
    Примечания
    -0.81
     '{@
    -0.77
    WebVitals
    -0.77
    Bronnen
    -0.76
     unknownFields
    -0.72
     дописавши
    -0.68
    Referanser
    -0.68
    HTH
    -0.65
    IBarButtonItem
    -0.65
    Referencias
    -0.63
    POSITIVE LOGITS
    ️⃣
    0.65
    ⃣
    0.54
    COMPAT
    0.52
    sama
    0.47
    
    0.46
    ayout
    0.43
    pojo
    0.43
     Adventures
    0.42
    EFIAPI
    0.42
     Monde
    0.41
    Activations Density 11.042%

    No Known Activations