© 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. 4-GEMMASCOPE-TRANSCODER-16K
    4. 14011
    Prev
    Next
    INDEX
    Explanations

    instances of storytelling, including the act of telling a story, a summary of a story, or references to the way a story is told.

    oai_token-act-pair · gemini-2.0-flash

    narratives and explanations

    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
     gli
    -0.57
    ScopeManager
    -0.50
    adze
    -0.49
     di
    -0.48
     lecciones
    -0.48
    зю
    -0.46
     realize
    -0.46
    
    -0.45
    RESUMO
    -0.45
     <<<<<<<<<<<<<<
    -0.45
    POSITIVE LOGITS
    OGND
    0.93
     يتيمه
    0.91
    ]")]
    0.84
    ]-->
    0.80
    endpush
    0.78
     Audiodateien
    0.77
    脚注の使い方
    0.75
     समीक्षाओं
    0.74
     initComponents
    0.71
    󠁴
    0.71
    Activations Density 3.428%

    No Known Activations