© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7706
    Prev
    Next
    INDEX
    Explanations

    references to death and the afterlife

    oai_token-act-pair · gemini-2.0-flash

    dead

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     dead
    -3.31
    dead
    -2.94
     Dead
    -2.80
    Dead
    -2.75
     DEAD
    -2.53
    DEAD
    -2.30
     muertos
    -1.63
     мерт
    -1.62
     muerto
    -1.59
     deceased
    -1.48
    POSITIVE LOGITS
    BeginContext
    0.62
    SequentialGroup
    0.59
    esModule
    0.58
     ostrich
    0.56
     stork
    0.54
     ويكيميديا
    0.53
     nonUne
    0.53
     homolog
    0.53
     Assignee
    0.53
    épend
    0.51
    Activations Density 1.863%

    No Known Activations