© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15969
    Prev
    Next
    INDEX
    Explanations

    words related to safety, protection, risk, or law.

    oai_token-act-pair · gemini-2.0-flash

    safety and protection

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     geldig
    -0.49
     Narod
    -0.48
    cipar
    -0.47
    testens
    -0.47
     링크
    -0.47
     Perfon
    -0.46
    Pautan
    -0.46
    zdroj
    -0.45
    URLException
    -0.44
     egne
    -0.43
    POSITIVE LOGITS
     AssemblyCulture
    0.69
    SourceChecksum
    0.66
    oa̍t
    0.61
    ValueStyle
    0.60
    InputTagHelper
    0.60
    initComponents
    0.60
    Билгалдахарш
    0.59
    Gön
    0.59
    機
    0.57
    DebuggerNonUser
    0.57
    Activations Density 7.122%

    No Known Activations