© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12727
    Prev
    Next
    INDEX
    Explanations

    words that suggest intensity or a high degree of something

    oai_token-act-pair · gemini-2.0-flash

    degree or intensity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     ujednoznacz
    -0.84
     Normdatei
    -0.84
    GraphicsUnit
    -0.81
    SBATCH
    -0.79
     nahilalakip
    -0.68
    ագրություններ
    -0.67
    IsMutable
    -0.64
    issionais
    -0.63
    InitVars
    -0.63
    ticides
    -0.63
    POSITIVE LOGITS
     tantos
    0.61
     tão
    0.54
     tanto
    0.52
     much
    0.51
     tanta
    0.51
     tantas
    0.50
     τό
    0.49
    這麼
    0.48
    destruction
    0.47
     so
    0.46
    Activations Density 1.476%

    No Known Activations