© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4047
    Prev
    Next
    INDEX
    Explanations

    a grab bag of somewhat random proper nouns, domain names, numbers, adjectives, and verbs.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     propOrder
    -0.81
    WithIOException
    -0.63
    ✭✭
    -0.62
    Personendaten
    -0.57
    Rhestr
    -0.57
    fjspx
    -0.54
    出版年
    -0.51
     Roskov
    -0.51
     Universitaria
    -0.48
     Chwiliwch
    -0.48
    POSITIVE LOGITS
    tes
    0.90
    te
    0.88
    ti
    0.88
    ting
    0.86
    ta
    0.84
    ten
    0.80
    ty
    0.77
    ted
    0.75
    tle
    0.66
    ts
    0.66
    Activations Density 6.115%

    No Known Activations