© 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. 10222
    Prev
    Next
    INDEX
    Explanations

    capitalized letters, especially acronyms and initialisms

    oai_token-act-pair · gemini-2.0-flash

    Acronyms/initials appearing in names

    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
     
    -2.25
     D
    -1.88
     R
    -1.80
     I
    -1.78
     (
    -1.77
     H
    -1.75
      
    -1.74
     L
    -1.73
     A
    -1.73
     F
    -1.73
    POSITIVE LOGITS
     ―――――
    2.53
     Efq
    2.45
     auffi
    2.25
     Monfieur
    2.23
     ainfi
    2.23
     Anſ
    2.22
     Theſe
    2.22
     myſelf
    2.22
     itſelf
    2.19
     doubtnut
    2.17
    Activations Density 1.108%

    No Known Activations