© 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. 5711
    Prev
    Next
    INDEX
    Explanations

    C code syntax, specifically related to variable assignment, conditional statements, and file operations

    oai_token-act-pair · gemini-2.0-flash

    tokens often representing prefixes in programming or text

    np_token-act-pair-logits · gpt-4o-mini
    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
     Monfieur
    -1.38
     CHAPITRE
    -1.34
     ainfi
    -1.30
     Theſe
    -1.29
     Anſ
    -1.25
     Efq
    -1.24
     Reſ
    -1.24
     avoient
    -1.23
     Diſ
    -1.23
     étoient
    -1.23
    POSITIVE LOGITS
     de
    0.70
     la
    0.69
     des
    0.65
     le
    0.57
     en
    0.56
     est
    0.53
     cor
    0.53
     les
    0.52
     que
    0.50
     par
    0.47
    Activations Density 10.551%

    No Known Activations