© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12457
    Prev
    Next
    INDEX
    Explanations

    references to places or neighborhoods

    oai_token-act-pair · gemini-2.0-flash

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    TargetException
    -0.76
     Мексичка
    -0.69
     photolibrary
    -0.64
    ̈́
    -0.62
     otomatig
    -0.61
    />";
    -0.61
    bibitem
    -0.60
     XNUMX
    -0.59
     HasFactory
    -0.58
    曖昧さ回避
    -0.57
    POSITIVE LOGITS
    rshire
    0.52
     متعلقه
    0.49
    supset
    0.48
     NHS
    0.47
     estre
    0.47
     Chwiliwch
    0.46
    SharedCtor
    0.46
     EconPapers
    0.45
     Har
    0.45
    otho
    0.45
    Activations Density 1.137%

    No Known Activations