© 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. 11476
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical symbols after the characters that usually represent a space

    oai_token-act-pair · gemini-2.0-flash

    numeric terms or identifiers

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

    Numbers and code

    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
    ſelf
    -0.76
    PerformLayout
    -0.76
     دیکھیے
    -0.75
     ivelany
    -0.75
    rungsseite
    -0.74
    ArgsConstructor
    -0.73
    
    -0.71
     Majefty
    -0.69
     Fifth
    -0.68
    !*\
    -0.68
    POSITIVE LOGITS
     two
    0.46
     intptr
    0.43
     ké
    0.41
     Google
    0.40
    dua
    0.38
     szóci
    0.38
    elezo
    0.37
    VERTIS
    0.36
    entile
    0.36
     menj
    0.36
    Activations Density 2.394%

    No Known Activations