© 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
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 198
    Prev
    Next
    INDEX
    Explanations

    seemingly random alphanumeric IDs followed by the letter 'a'

    oai_token-act-pair · gemini-2.0-flash

    Zeros

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Medium
    -0.45
     limone
    -0.45
     stof
    -0.45
     veda
    -0.44
    best
    -0.44
     pemberian
    -0.43
     igång
    -0.43
    Osob
    -0.42
    Américaine
    -0.42
    nestjs
    -0.41
    POSITIVE LOGITS
    TagMode
    1.05
    TestingModule
    0.98
    MigrationBuilder
    0.90
    ValueStyle
    0.88
     AssemblyCulture
    0.79
     BoxDecoration
    0.79
    numerusform
    0.79
    UnusedPrivate
    0.79
    IsContent
    0.77
    ContentAsync
    0.77
    Activations Density 0.137%

    No Known Activations