© 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. 15774
    Prev
    Next
    INDEX
    Explanations

    the letter f, the word industrial, and numbers in math contexts

    oai_token-act-pair · gemini-2.0-flash

    industrial

    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
     
    -2.14
     (
    -1.77
     d
    -1.66
     A
    -1.63
     l
    -1.63
      
    -1.63
    ,
    -1.56
     "
    -1.51
     f
    -1.50
     B
    -1.50
    POSITIVE LOGITS
     Monfieur
    3.91
     myſelf
    3.88
     Efq
    3.77
     purpoſe
    3.64
     houſe
    3.63
     itſelf
    3.63
     pleaſure
    3.59
     ſtate
    3.55
     auffi
    3.53
     Reſ
    3.52
    Activations Density 11.972%

    No Known Activations