© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5512
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to trains

    oai_token-act-pair · gemini-2.0-flash

    trains/movement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     ―――――
    -1.49
     ་་
    -1.33
     itſelf
    -1.31
    ſelf
    -1.29
     ――――
    -1.24
     Efq
    -1.20
     ſind
    -1.19
    ſelves
    -1.19
     iſt
    -1.18
     photolibrary
    -1.18
    POSITIVE LOGITS
     
    1.09
     a
    1.01
     the
    1.00
     I
    0.88
      
    0.80
     A
    0.75
     "
    0.75
     an
    0.75
     my
    0.74
    ed
    0.73
    Activations Density 1.039%

    No Known Activations