© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7003
    Prev
    Next
    INDEX
    Explanations

    what appears to be code

    oai_token-act-pair · gemini-2.0-flash

    whitespace and formatting characters

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

    Code/math symbols

    np_max-act-logits · gemini-2.0-flash

    punctuation

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    rungsseite
    -1.13
    Personensuche
    -1.13
     للمعارف
    -1.09
    Personendaten
    -1.09
    存于互联网档案馆
    -1.09
     betweenstory
    -1.05
    ſelves
    -1.02
     tartalomajánló
    -1.00
    ſelf
    -0.99
    __':
    -0.99
    POSITIVE LOGITS
     
    0.80
     -
    0.66
     n
    0.65
     +
    0.62
    1
    0.59
     *
    0.59
     [
    0.57
    2
    0.57
     _
    0.57
    ↵↵
    0.56
    Activations Density 29.120%

    No Known Activations