© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12553
    Prev
    Next
    INDEX
    Explanations

    words related to risk taking and potential danger.

    oai_token-act-pair · gemini-2.0-flash

    Car-related events

    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
    PerformLayout
    -0.60
     Vikipedi
    -0.58
     HasFactory
    -0.57
     Stopping
    -0.55
     stopping
    -0.55
     Stoppers
    -0.54
    SpringRunner
    -0.53
     stops
    -0.52
     @"/
    -0.52
    terase
    -0.51
    POSITIVE LOGITS
    IonicModule
    0.51
     Lottie
    0.50
    +#+
    0.50
     téléphonique
    0.50
    Begriffsklä
    0.47
     الحره
    0.47
     zove
    0.46
    المناصب
    0.46
    ย์
    0.46
    Espagne
    0.45
    Activations Density 2.422%

    No Known Activations