© 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. 11350
    Prev
    Next
    INDEX
    Explanations

    words frequently used in scientific research papers, such as "the", "study", "to", "effects

    oai_token-act-pair · gemini-2.0-flash

    concepts related to research investigations

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

    the

    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
    uns
    -0.51
    ]+=
    -0.48
     ErrIntOverflow
    -0.47
    onde
    -0.47
     déroule
    -0.46
     procédure
    -0.45
     vyš
    -0.45
    System
    -0.44
    sedown
    -0.44
     éto
    -0.42
    POSITIVE LOGITS
     existence
    0.73
    AsUp
    0.65
     relationship
    0.64
     presence
    0.62
     role
    0.62
    toHaveBeenCalled
    0.60
    InvalidProtocol
    0.60
    ็จ
    0.60
     nature
    0.59
    ="@+
    0.59
    Activations Density 3.114%

    No Known Activations