© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10745
    Prev
    Next
    INDEX
    Explanations

    patent-related documentation regarding material composition.

    oai_token-act-pair · gemini-2.0-flash

    composition

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     pleaſure
    -0.75
     Савезне
    -0.63
    iastical
    -0.60
    WebVitals
    -0.59
    >//
    -0.59
     Diſ
    -0.59
     AssemblyCulture
    -0.57
     ſmall
    -0.57
     stiefel
    -0.56
     ſtate
    -0.55
    POSITIVE LOGITS
     based
    1.34
     Based
    1.19
     BASED
    1.14
    based
    1.12
    Based
    1.09
    BASED
    0.92
     basado
    0.82
     basé
    0.79
     basée
    0.77
     baseado
    0.77
    Activations Density 3.084%

    No Known Activations