© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1622
    Prev
    Next
    INDEX
    Explanations

    code snippets and economic language

    oai_token-act-pair · gemini-2.0-flash

    programming environments

    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
    +#+#
    -0.88
    StoryboardSegue
    -0.81
     Roskov
    -0.71
    تقاوى
    -0.68
    SourceChecksum
    -0.67
     gynhyrchwyd
    -0.66
    hyrchwyd
    -0.63
    enterOuterAlt
    -0.63
    tamol
    -0.62
     Administrativna
    -0.62
    POSITIVE LOGITS
    OrUpdate
    0.46
     JADX
    0.45
     biling
    0.43
     výraz
    0.42
    Autowired
    0.40
     wiesz
    0.40
    ueta
    0.40
    你知道
    0.40
    eachtet
    0.40
     우
    0.39
    Activations Density 1.607%

    No Known Activations