© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5963
    Prev
    Next
    INDEX
    Explanations

    table-like structures marked with dashes ('-'), pluses ('+'), and pipes ('|')

    oai_token-act-pair · gemini-2.0-flash

    data tables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ↵↵
    -0.54
    A
    -0.52
    F
    -0.48
    ​
    -0.47
    D
    -0.45
     
    -0.45
    ↵
    -0.45
    ↵↵↵
    -0.45
    I
    -0.44
    N
    -0.44
    POSITIVE LOGITS
     itſelf
    1.31
     myſelf
    1.25
     raiſ
    1.03
     themſelves
    1.01
     Jefus
    0.98
     ſta
    0.98
     pleaſure
    0.94
     purpoſe
    0.94
    LookAnd
    0.93
     ſtate
    0.93
    Activations Density 2.048%

    No Known Activations