© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9237
    Prev
    Next
    INDEX
    Explanations

    personal pronouns being used to describe the writer's experiences and opinions

    oai_token-act-pair · gemini-2.0-flash

    organizational roles

    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
    WithMany
    -0.47
    enumi
    -0.45
     pri
    -0.43
    ActionEvent
    -0.42
    LayoutStyle
    -0.39
    "]').
    -0.39
     Przy
    -0.38
     ha
    -0.38
    isle
    -0.38
    +");
    -0.37
    POSITIVE LOGITS
    ftagPool
    0.91
     Efq
    0.82
     myſelf
    0.76
     themſelves
    0.75
     itſelf
    0.75
     pleaſure
    0.73
     uſed
    0.73
     himſelf
    0.73
     becauſe
    0.72
     unſ
    0.71
    Activations Density 1.841%

    No Known Activations