© 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. 7700
    Prev
    Next
    INDEX
    Explanations

    sentences that describe upsetting or harmful experiences, especially accidents

    oai_token-act-pair · gemini-2.0-flash

    Accidents and tragedies

    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
     accident
    -1.97
     Accident
    -1.82
    Accident
    -1.75
    accident
    -1.75
     disaster
    -1.70
     ACCIDENT
    -1.59
     accidents
    -1.55
     Disaster
    -1.54
     catastrophe
    -1.48
     Accidents
    -1.47
    POSITIVE LOGITS
     skinny
    0.37
    colorbar
    0.35
    <bos>
    0.35
    cault
    0.34
     대한
    0.33
     corral
    0.33
    BCC
    0.33
    EMU
    0.32
    AC
    0.32
    werbe
    0.32
    Activations Density 1.571%

    No Known Activations