© 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. 6500
    Prev
    Next
    INDEX
    Explanations

    words or phrases starting with "co-", especially words related to employment or organization membership

    oai_token-act-pair · gemini-2.0-flash

    collaboration/work/research

    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
    তথ্যসূত্র
    -0.69
     co
    -0.61
    InSection
    -0.55
     resourceCulture
    -0.52
     Signalez
    -0.51
     MainAxisSize
    -0.50
     arşivlendi
    -0.48
    Especificações
    -0.47
    étrie
    -0.47
     Profiles
    -0.46
    POSITIVE LOGITS
    VideoCapture
    0.60
     kasarigan
    0.59
    oplayer
    0.59
    contentLoaded
    0.57
    ⓧ
    0.54
    Rüyada
    0.53
    ordinated
    0.52
    ніципалі
    0.52
    inci
    0.51
    SharedCtor
    0.50
    Activations Density 0.635%

    No Known Activations