© 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. 5660
    Prev
    Next
    INDEX
    Explanations

    the phrase "so long as"

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "long"

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

    as/so

    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
    MessageTagHelper
    -0.64
    EndContext
    -0.59
    ItemBackground
    -0.51
    ########.
    -0.48
    Provided
    -0.45
    :✨
    -0.45
    astify
    -0.44
    queryInterface
    -0.43
     createContext
    -0.42
     Provided
    -0.40
    POSITIVE LOGITS
     long
    2.91
    long
    2.44
     LONG
    1.92
    Long
    1.88
     Long
    1.79
    LONG
    1.77
     longue
    1.52
     longa
    1.52
     longterm
    1.50
     longo
    1.49
    Activations Density 1.190%

    No Known Activations