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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10744
    Prev
    Next
    INDEX
    Explanations

    sentences that start with coordinating conjunctions, especially "but"

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "also"

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

    also

    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
    minecraft
    -0.45
    upyter
    -0.43
     More
    -0.43
    jstor
    -0.43
     Q
    -0.43
     dans
    -0.43
    None
    -0.42
     nem
    -0.42
    zim
    -0.41
    More
    -0.41
    POSITIVE LOGITS
     also
    1.94
    also
    1.56
     alfo
    1.53
    Also
    1.51
     alſo
    1.50
     likewise
    1.47
     также
    1.46
     Also
    1.45
     également
    1.39
     también
    1.37
    Activations Density 1.205%

    No Known Activations