© 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. 249
    Prev
    Next
    INDEX
    Explanations

    snippets of code in a variety of programming languages

    oai_token-act-pair · gemini-2.0-flash

    code syntax

    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
     derfor
    -0.44
     beina
    -0.42
    maier
    -0.41
     públicas
    -0.40
    memoized
    -0.39
     famiglie
    -0.39
     explicar
    -0.38
    žuje
    -0.38
    GraphicsUnit
    -0.38
     explique
    -0.37
    POSITIVE LOGITS
    RuleContext
    0.72
     تانيه
    0.66
    ühen
    0.64
    RenderAtEndOf
    0.62
     مرئيه
    0.62
    GOTREF
    0.60
     betweenstory
    0.60
     LUMP
    0.60
    CDA
    0.58
     rowspan
    0.57
    Activations Density 24.377%

    No Known Activations