© 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. 15845
    Prev
    Next
    INDEX
    Explanations

    apologies or words of regret

    oai_token-act-pair · gemini-2.0-flash

    sorry

    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
     AssemblyCulture
    -0.93
    rungsseite
    -0.89
     propOrder
    -0.87
    Jeografia
    -0.85
    enumi
    -0.84
     nahilalakip
    -0.81
    RectangleBorder
    -0.79
    OGND
    -0.79
    setVerticalGroup
    -0.78
     defaultstate
    -0.77
    POSITIVE LOGITS
     to
    0.47
     for
    0.46
     we
    0.44
     я
    0.41
     mixta
    0.38
     I
    0.36
     tengo
    0.35
     they
    0.35
     true
    0.35
     panier
    0.34
    Activations Density 1.955%

    No Known Activations