© 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. 5324
    Prev
    Next
    INDEX
    Explanations

    mentions of character death within the context of a narrative, particularly in games and movies

    oai_token-act-pair · gemini-2.0-flash

    irrelevant or unrecognized content

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

    Movie and stories context

    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
    EDEFAULT
    -0.48
    Cypress
    -0.48
    hoga
    -0.48
     committed
    -0.48
     estekak
    -0.45
    ვი
    -0.45
     Moines
    -0.44
    ソッド
    -0.44
     publicités
    -0.43
     pilotes
    -0.43
    POSITIVE LOGITS
     للاسماء
    0.72
    \{\\
    0.61
    клопе
    0.60
     EconPapers
    0.55
    ferential
    0.54
    CompleteListener
    0.53
     Tin
    0.53
     Chwiliwch
    0.52
    amoan
    0.51
     figuring
    0.51
    Activations Density 1.075%

    No Known Activations