© 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. 11400
    Prev
    Next
    INDEX
    Explanations

    a wide range of words that often occur near numbers or ages.

    oai_token-act-pair · gemini-2.0-flash

    references to the concept of 'middle'

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

    mid age

    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
    uxxxx
    -0.87
    tagHelperRunner
    -0.82
    Personensuche
    -0.80
    /*
    -0.69
    :✨
    -0.68
     distanciation
    -0.68
    InitVars
    -0.68
    URLException
    -0.67
     isInitialized
    -0.66
    SerializedSize
    -0.65
    POSITIVE LOGITS
     middle
    0.98
    middle
    0.89
     Mid
    0.85
     mid
    0.84
    Mid
    0.78
    Middle
    0.77
    mid
    0.73
     per
    0.71
     forty
    0.71
     Middle
    0.69
    Activations Density 1.585%

    No Known Activations