© 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. 5411
    Prev
    Next
    INDEX
    Explanations

    references to the Trayvon Martin case and the legal aftermath

    oai_token-act-pair · gemini-2.0-flash

    Tragedies/shootings

    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
    !*\
    -0.56
    IUrlHelper
    -0.52
    findpost
    -0.52
     Mérimée
    -0.51
    enoord
    -0.48
    UseVisualStyle
    -0.48
    AnchorStyles
    -0.48
    lış
    -0.47
     circuits
    -0.47
    ArgsConstructor
    -0.46
    POSITIVE LOGITS
    Trag
    0.62
    windowFixed
    0.61
    Хьажоргаш
    0.59
     tragedies
    0.56
     shooting
    0.56
     tragic
    0.54
     vanishing
    0.53
     tragedy
    0.53
    FontOfSize
    0.53
     shootings
    0.52
    Activations Density 1.233%

    No Known Activations