© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16085
    Prev
    Next
    INDEX
    Explanations

    about war crimes in specific regions with possible involvement of organizations like the UN.

    oai_token-act-pair · gemini-2.0-flash

    conflicts, politics, regions

    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
    SourceChecksum
    -0.93
    contentLoaded
    -0.69
    jspx
    -0.66
     resourceCulture
    -0.63
    fjspx
    -0.58
    rzost
    -0.57
    ulism
    -0.56
    ($__
    -0.56
    ortun
    -0.50
    (:,:,
    -0.50
    POSITIVE LOGITS
    nocache
    0.48
    ---*/
    0.47
    bumptech
    0.47
    GCT
    0.46
    setPadding
    0.46
    更何况
    0.46
    쩌
    0.46
    Ụ
    0.43
    angerie
    0.43
     Bock
    0.43
    Activations Density 1.920%

    No Known Activations