© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5250
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs like "have", "has" "had", "would", and "were"

    oai_token-act-pair · gemini-2.0-flash

    had

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Must
    -0.83
    adaptiveStyles
    -0.81
    must
    -0.81
    Must
    -0.79
     AssemblyTitle
    -0.75
     <=",
    -0.73
    MUST
    -0.72
     must
    -0.71
     EClass
    -0.68
     muſt
    -0.68
    POSITIVE LOGITS
     had
    2.45
    Had
    2.14
    had
    2.13
     Had
    2.05
     HAD
    1.79
    HAD
    1.49
     hadden
    1.27
     hatte
    1.27
     hatten
    1.27
     είχε
    1.20
    Activations Density 2.555%

    No Known Activations