© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12453
    Prev
    Next
    INDEX
    Explanations

    "responsibility" as a noun and references to responsibility.

    oai_token-act-pair · gemini-2.0-flash

    responsibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    fromnode
    -0.67
    "});
    -0.62
    >[]
    -0.61
    %?
    -0.60
    oredCriteria
    -0.60
     مشين
    -0.57
    Yourself
    -0.57
     zelf
    -0.57
    :✨
    -0.57
    бат
    -0.56
    POSITIVE LOGITS
     estekak
    0.57
    enumi
    0.50
    ess
    0.48
    PS
    0.48
     BoxDecoration
    0.47
    XtraReports
    0.46
    etting
    0.46
    creativecommons
    0.46
    ss
    0.43
    etts
    0.41
    Activations Density 2.002%

    No Known Activations