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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11304
    Prev
    Next
    INDEX
    Explanations

    punctuation after a noun

    oai_token-act-pair · gemini-2.0-flash

    sentence endings

    np_token-act-pair-logits · gpt-4o-mini
    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
     propOrder
    -0.64
    ]=>
    -0.60
    StackNavigator
    -0.57
     fallu
    -0.50
     didst
    -0.48
    ved
    -0.48
    פס
    -0.47
     underwent
    -0.46
    ímp
    -0.45
    mos
    -0.44
    POSITIVE LOGITS
     Audiodateien
    0.63
     المعيارى
    0.56
    EReference
    0.56
    addContainerGap
    0.50
    luß
    0.49
    جوايز
    0.48
    working
    0.48
    órmula
    0.48
     autrement
    0.48
    ahead
    0.47
    Activations Density 2.205%

    No Known Activations