© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12409
    Prev
    Next
    INDEX
    Explanations

    words associated with scientific research and legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    forensic/scientific analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    +#+#
    -0.57
    NUMX
    -0.49
    плуата
    -0.46
    {§
    -0.46
    isseaux
    -0.45
    omitempty
    -0.44
    ientôt
    -0.43
    زالة
    -0.43
     genannt
    -0.43
    ativement
    -0.43
    POSITIVE LOGITS
    <bos>
    1.34
    Билгалдахарш
    0.70
    Geplaatst
    0.68
     الحره
    0.66
    Cyfeiriadau
    0.65
    fjspx
    0.65
     referenties
    0.62
    onAttach
    0.61
     plein
    0.61
     kaarangay
    0.60
    Activations Density 5.814%

    No Known Activations