© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10360
    Prev
    Next
    INDEX
    Explanations

    the neuron is focused on stories, and words describing abuse of children and slavery.

    oai_token-act-pair · gemini-2.0-flash

    slavery/mistreatment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     kaynağından
    -0.67
    İstinadlar
    -0.64
    IUrlHelper
    -0.60
    IBAction
    -0.58
    zyden
    -0.53
    脚注の使い方
    -0.52
    ChildScrollView
    -0.51
     समीक्षक
    -0.51
    Ausgabe
    -0.50
    iotensin
    -0.49
    POSITIVE LOGITS
    makeText
    0.58
    achau
    0.54
    sunter
    0.49
     unspeak
    0.49
    نش
    0.48
    сылкі
    0.48
    import
    0.47
     CEM
    0.46
     suffering
    0.46
     SEE
    0.45
    Activations Density 0.729%

    No Known Activations