© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12345
    Prev
    Next
    INDEX
    Explanations

    locations in California and category tags

    oai_token-act-pair · gemini-2.0-flash

    California locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     San
    -0.59
     Orange
    -0.55
    San
    -0.54
     san
    -0.51
    san
    -0.50
     Riverside
    -0.46
    SAN
    -0.46
     Longo
    -0.45
    Orange
    -0.45
     Ing
    -0.44
    POSITIVE LOGITS
     الحره
    0.95
     autorytatywna
    0.87
     ExecuteAsync
    0.79
    ThroughAttribute
    0.78
    AndEndTag
    0.76
     متعلقه
    0.74
    出版年
    0.74
    Manbalar
    0.72
     doubtnut
    0.68
    ագրություններ
    0.68
    Activations Density 1.061%

    No Known Activations