© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7972
    Prev
    Next
    INDEX
    Explanations

    code snippets and references to HTML

    oai_token-act-pair · gemini-2.0-flash

    record, head

    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
     незавершена
    -0.90
    SharedDtor
    -0.87
     faſt
    -0.85
     myſelf
    -0.84
    uests
    -0.84
     pleaſure
    -0.83
     Efq
    -0.82
    UrlResolution
    -0.80
    latego
    -0.80
    WriteTagHelper
    -0.79
    POSITIVE LOGITS
     vostri
    0.58
    ane
    0.55
    isa
    0.53
     might
    0.53
     $
    0.52
    цер
    0.50
    co
    0.50
    gg
    0.49
    americanos
    0.49
     as
    0.49
    Activations Density 0.737%

    No Known Activations