© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3663
    Prev
    Next
    INDEX
    Explanations

    sentences related to legal proceedings, debates, discussion and logical conclusions .

    oai_token-act-pair · gemini-2.0-flash

    legal arguments/discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    expandindo
    -0.61
    ]")]
    -0.54
    +:+
    -0.51
    KURZBESCHREIBUNG
    -0.51
     jadx
    -0.50
    httphttps
    -0.48
    )]:
    -0.46
     raged
    -0.44
     متعلقه
    -0.43
    //</
    -0.42
    POSITIVE LOGITS
     bandes
    0.62
    GEBURTSDATUM
    0.62
    ablemente
    0.59
    رشف
    0.58
    chọn
    0.58
    ględ
    0.57
    msgTypes
    0.56
    iburg
    0.56
    antMatchers
    0.53
     Spending
    0.52
    Activations Density 4.829%

    No Known Activations