© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16179
    Prev
    Next
    INDEX
    Explanations

    words or abbreviation sequences written in all-caps

    oai_token-act-pair · gemini-2.0-flash

    DON

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    virons
    -0.42
     sy
    -0.39
    ía
    -0.39
    stdc
    -0.39
     er
    -0.38
    LLABLE
    -0.38
    tho
    -0.38
    ça
    -0.38
    sie
    -0.37
    alist
    -0.36
    POSITIVE LOGITS
     kasarigan
    0.72
     betweenstory
    0.71
     définiti
    0.69
    AND
    0.67
     vœux
    0.67
    transQ
    0.66
     fédé
    0.66
    ES
    0.66
     financières
    0.66
     stället
    0.66
    Activations Density 2.761%

    No Known Activations