© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 925
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating data analysis and reporting facts

    oai_token-act-pair · gemini-2.0-flash

    Chinese names

    np_max-act-logits · 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
     myſelf
    -1.28
     Efq
    -1.23
     itſelf
    -1.16
     purpoſe
    -1.16
     Theſe
    -1.15
     ſeveral
    -1.13
     uſed
    -1.13
     himſelf
    -1.11
     Monfieur
    -1.07
     themſelves
    -1.06
    POSITIVE LOGITS
     Liu
    0.59
     Wang
    0.59
     Li
    0.56
     Zhang
    0.56
     Wu
    0.55
     Xia
    0.54
     Xu
    0.54
     Huang
    0.54
     Chen
    0.54
     Wei
    0.48
    Activations Density 13.099%

    No Known Activations