© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7642
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating negative medical outcomes or risk

    oai_token-act-pair · gemini-2.0-flash

    poor/worse

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    IntoConstraints
    -0.60
     comuniques
    -0.59
    NameInMap
    -0.58
     surla
    -0.55
     AssemblyVersion
    -0.52
    addCriterion
    -0.52
    ]})
    -0.51
     auxquels
    -0.50
    writeFieldEnd
    -0.49
     newOwner
    -0.49
    POSITIVE LOGITS
     outcomes
    0.86
     outcome
    0.85
     prognosis
    0.81
     Outcome
    0.81
     Outcomes
    0.80
     progn
    0.79
     prognostic
    0.68
    outcome
    0.67
    Outcome
    0.66
    outcomes
    0.65
    Activations Density 2.070%

    No Known Activations