© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1814
    Prev
    Next
    INDEX
    Explanations

    discontiguous sections of text with some linguistic or topic coherence or it finds many numbers near each other

    oai_token-act-pair · gemini-2.0-flash

    beginning of texts

    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
    帖最后由
    -0.77
    Personendaten
    -0.57
    OGND
    -0.53
     ſtate
    -0.53
     purpoſe
    -0.51
     bygger
    -0.50
     agré
    -0.50
     AssemblyCompany
    -0.49
    postmedia
    -0.49
     TextAppearance
    -0.48
    POSITIVE LOGITS
    日閲覧
    0.57
    Including
    0.51
    rollup
    0.48
    BitConverter
    0.47
     madd
    0.47
     directories
    0.47
    codings
    0.46
     المعيارى
    0.46
    Jährige
    0.45
     shilling
    0.45
    Activations Density 33.814%

    No Known Activations