© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 294
    Prev
    Next
    INDEX
    Explanations

    examples or references to queries and code, especially SQL

    oai_token-act-pair · gemini-2.0-flash

    SQL code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     nahilalakip
    -0.95
    CppMethod
    -0.93
    ⓧ
    -0.92
    Hentet
    -0.87
    setVerticalGroup
    -0.86
    MockBean
    -0.83
    expandindo
    -0.83
     itſelf
    -0.80
    ſelf
    -0.79
     disambiguazione
    -0.79
    POSITIVE LOGITS
     activity
    0.43
     sit
    0.41
     ro
    0.40
     /
    0.40
    ).
    0.40
     доста
    0.38
    ‍
    0.38
    System
    0.38
     kebenaran
    0.38
    '
    0.37
    Activations Density 0.852%

    No Known Activations