© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5564
    Prev
    Next
    INDEX
    Explanations

    phrases containing words associated with gore and the human body or medicine

    oai_token-act-pair · gemini-2.0-flash

    related to dead bodies

    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
     Body
    -3.09
     body
    -3.08
    Body
    -3.02
    body
    -2.94
     bodies
    -2.91
     Bodies
    -2.88
     BODY
    -2.84
    bodies
    -2.69
    BODY
    -2.66
    Bodies
    -2.55
    POSITIVE LOGITS
     fır
    0.38
    ľ
    0.35
     vœux
    0.33
     leopardo
    0.32
     nélk
    0.31
     infeksi
    0.31
     rajut
    0.30
     lámpara
    0.30
    optString
    0.30
     médec
    0.29
    Activations Density 2.072%

    No Known Activations