© 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. 10192
    Prev
    Next
    INDEX
    Explanations

    the word "versus", and the Roman numeral "I"

    oai_token-act-pair · gemini-2.0-flash

    versus

    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
     
    -0.82
     I
    -0.60
     M
    -0.60
     D
    -0.59
     F
    -0.59
     ​​
    -0.57
     V
    -0.57
     N
    -0.56
     O
    -0.56
     l
    -0.55
    POSITIVE LOGITS
     auffi
    1.03
     quæ
    1.02
     ainfi
    0.92
     ſtate
    0.88
     pegat
    0.85
     viſ
    0.85
     ſche
    0.84
     cauſe
    0.83
     deſt
    0.80
     ſet
    0.79
    Activations Density 4.880%

    No Known Activations