© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4689
    Prev
    Next
    INDEX
    Explanations

    first person perspective in personal anecdotes

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "turn"

    np_token-act-pair-logits · gpt-4o-mini

    related to "turns"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    PullParser
    -0.75
    FunctionFlags
    -0.70
    rawDesc
    -0.69
     kaynağından
    -0.65
    IntoConstraints
    -0.64
     voeren
    -0.62
    ongyang
    -0.62
     ་་
    -0.61
     Baillargeon
    -0.61
     FG
    -0.60
    POSITIVE LOGITS
     turns
    0.61
     Turned
    0.56
     Turns
    0.55
     turned
    0.52
    Turned
    0.52
    turns
    0.50
     me
    0.50
    Turns
    0.50
    EndContext
    0.48
     turn
    0.47
    Activations Density 1.811%

    No Known Activations