© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12340
    Prev
    Next
    INDEX
    Explanations

    code snippets including references to functions, classes and APIs

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
     i
    -0.84
     I
    -0.77
     T
    -0.68
     A
    -0.67
     in
    -0.66
     and
    -0.66
     O
    -0.65
     V
    -0.63
     M
    -0.62
     for
    -0.62
    POSITIVE LOGITS
     Shakspeare
    1.10
    WebVitals
    1.10
     فريبيس
    1.07
    RetentionPolicy
    1.05
     Shaksp
    0.96
    PerformLayout
    0.94
     photolibrary
    0.94
     Efq
    0.92
    ConstraintMaker
    0.92
    NameInMap
    0.89
    Activations Density 6.658%

    No Known Activations