© 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. 12606
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "human" and its relations, along with death and the killing of insects via electricity.

    oai_token-act-pair · gemini-2.0-flash

    violence and killing

    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
     dead
    -2.23
     death
    -2.02
    dead
    -1.93
     Dead
    -1.89
     deaths
    -1.87
    Dead
    -1.83
     DEAD
    -1.82
     deceased
    -1.81
    death
    -1.76
     Death
    -1.73
    POSITIVE LOGITS
    kadi
    0.47
    krat
    0.41
    YMS
    0.40
    σμα
    0.40
    oman
    0.40
     naga
    0.40
     kao
    0.39
     kors
    0.36
    انیا
    0.35
     kram
    0.35
    Activations Density 1.639%

    No Known Activations