© 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. 4740
    Prev
    Next
    INDEX
    Explanations

    phrases and words that warn the reader of a possible physical or financial risk.

    oai_token-act-pair · gemini-2.0-flash

    risks

    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
    proud
    -0.46
    éma
    -0.44
    hwar
    -0.44
    ThroughAttribute
    -0.44
     تضيفلها
    -0.44
    tagext
    -0.43
    waitKey
    -0.40
     Motion
    -0.40
     Proud
    -0.40
     proud
    -0.39
    POSITIVE LOGITS
     risk
    2.66
     risks
    2.41
     Risk
    2.33
    risk
    2.25
    Risk
    2.20
     RISK
    2.16
     Risks
    2.08
    risks
    2.05
     risked
    1.99
    RISK
    1.97
    Activations Density 0.576%

    No Known Activations