© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4319
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to risk or danger

    oai_token-act-pair · gemini-2.0-flash

    danger

    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
    riedenheit
    -0.68
    mergeFrom
    -0.65
     виправивши
    -0.62
    verständlich
    -0.60
     Pingback
    -0.59
    }}/>
    -0.57
     vägen
    -0.57
    AutoresizingMask
    -0.55
    monix
    -0.54
    Provenance
    -0.54
    POSITIVE LOGITS
     risk
    1.85
     risks
    1.62
     Risk
    1.56
    risk
    1.54
    Risk
    1.48
     RISK
    1.41
     danger
    1.41
     risked
    1.41
    RISK
    1.35
     Risks
    1.34
    Activations Density 0.741%

    No Known Activations