© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10241
    Prev
    Next
    INDEX
    Explanations

    celebrity tax problems

    oai_token-act-pair · gemini-2.0-flash

    celebrity tax problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    征
    -0.51
     vanske
    -0.41
    padek
    -0.40
     pribadi
    -0.40
    api
    -0.39
    meros
    -0.39
    滋
    -0.38
    چی
    -0.37
     murni
    -0.37
     kokona
    -0.37
    POSITIVE LOGITS
     lenker
    0.90
    expandindo
    0.88
     protoimpl
    0.84
     gyhoeddwyd
    0.83
    ChildScrollView
    0.81
     незавершена
    0.78
     disambiguazione
    0.75
    NUMX
    0.75
    WriteTagHelper
    0.73
    تقاوى
    0.72
    Activations Density 1.762%

    No Known Activations