© 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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7835
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly Java or C++ code involving symbol tables, data structures, and iteration

    oai_token-act-pair · gemini-2.0-flash

    entry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    -1.34
     Majefty
    -1.17
     itſelf
    -1.16
     pleaſure
    -1.15
     Efq
    -1.13
     Monfieur
    -1.13
     themſelves
    -1.07
     Houſe
    -1.06
     Anſ
    -1.05
     doubtnut
    -1.05
    POSITIVE LOGITS
     
    0.57
     The
    0.55
     [
    0.54
     "
    0.51
    通販
    0.48
    ↵↵
    0.48
     la
    0.47
    :
    0.47
     It
    0.47
     La
    0.47
    Activations Density 1.783%

    No Known Activations