© 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. 4658
    Prev
    Next
    INDEX
    Explanations

    words related to conflicts involving political groups and military forces

    oai_token-act-pair · gemini-2.0-flash

    group

    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
    IntoConstraints
    -0.77
    ValueGeneration
    -0.71
    addCriterion
    -0.71
     الرياضيه
    -0.64
     dAtA
    -0.63
    AndroidJUnit
    -0.62
    UnusedPrivate
    -0.60
    };*/
    -0.59
     Theſe
    -0.58
    tagext
    -0.58
    POSITIVE LOGITS
     NSMutable
    0.53
     intent
    0.52
    μά
    0.48
    Đ
    0.48
     vė
    0.48
    jface
    0.47
    辖
    0.46
     associated
    0.45
    ContentAsync
    0.44
    NSMutable
    0.44
    Activations Density 5.050%

    No Known Activations