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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13445
    Prev
    Next
    INDEX
    Explanations

    terms related lists of characters, ensembles, teams, or people who are associated with one another.

    oai_token-act-pair · gemini-2.0-flash

    groups of people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    liwości
    -0.60
    !*\
    -0.54
    __(/*!
    -0.53
    JspWriter
    -0.50
    原始内容存档于
    -0.49
    ToBounds
    -0.49
    исленность
    -0.49
    dataclass
    -0.49
     שוליים
    -0.48
    saraba
    -0.47
    POSITIVE LOGITS
     bezeichneter
    0.61
    脚注の使い方
    0.59
     InputDecoration
    0.57
     stepwise
    0.54
    ients
    0.52
     retenir
    0.52
     рода
    0.49
     dần
    0.48
     ktorí
    0.48
     politische
    0.48
    Activations Density 3.568%

    No Known Activations