© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13112
    Prev
    Next
    INDEX
    Explanations

    conjunctions, pronouns, and light verbs signalling continued conversation about a small number of active participants/subjects

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     pleaſure
    -0.72
    UnsafeEnabled
    -0.70
    />";
    -0.63
    //
    -0.60
    RTDA
    -0.59
     entanto
    -0.55
    labus
    -0.55
     myſelf
    -0.54
    复制代码
    -0.54
    antaranya
    -0.54
    POSITIVE LOGITS
    Bronnen
    0.64
     cref
    0.58
    NameInMap
    0.54
     manqué
    0.50
     AssemblyProduct
    0.49
     ostavi
    0.48
    ucid
    0.47
    Portale
    0.46
    mappedBy
    0.46
     Walkover
    0.46
    Activations Density 5.706%

    No Known Activations