© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11848
    Prev
    Next
    INDEX
    Explanations

    the word "or" or the word "if", and sometimes the word "available" or "shall"

    oai_token-act-pair · gemini-2.0-flash

    or/if

    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
     
    -0.81
      
    -0.79
    ↵
    -0.76
     (
    -0.68
     in
    -0.68
     R
    -0.68
     A
    -0.67
     "
    -0.65
     G
    -0.65
     T
    -0.64
    POSITIVE LOGITS
     auffi
    1.43
     Monfieur
    1.41
     Jefus
    1.41
     ainfi
    1.40
     faſt
    1.34
     itſelf
    1.31
     ſta
    1.27
     Diſ
    1.27
     iſt
    1.26
     ſche
    1.26
    Activations Density 0.405%

    No Known Activations