© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6327
    Prev
    Next
    INDEX
    Explanations

    mathematical equations, expressions, and variables.

    oai_token-act-pair · gemini-2.0-flash

    punctuation and formatting markers

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

    Math calculations

    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
     myſelf
    -1.16
     itſelf
    -1.09
     AssemblyCulture
    -1.07
    ंदीखरीदारी
    -1.05
    ſelves
    -1.05
     Monfieur
    -1.03
    WriteBarrier
    -1.02
     مشين
    -1.01
     poffible
    -1.00
    ſelf
    -0.98
    POSITIVE LOGITS
    <eos>
    0.65
     ,
    0.64
     “
    0.62
     
    0.57
    ↵↵
    0.55
    “
    0.53
     ‘
    0.52
    ”
    0.52
    .
    0.52
     Me
    0.52
    Activations Density 32.523%

    No Known Activations