© 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. 6827
    Prev
    Next
    INDEX
    Explanations

    the word "Center" or "Centre" and/or prepositions like "of", "for" and "in"

    oai_token-act-pair · gemini-2.0-flash

    for

    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
    prnewswire
    -0.59
    <bos>
    -0.56
     Pingback
    -0.56
     itſelf
    -0.56
     uſ
    -0.53
     juſt
    -0.53
    UnsafeEnabled
    -0.52
     ejus
    -0.52
     activities
    -0.52
     quæ
    -0.52
    POSITIVE LOGITS
     متعلقه
    0.81
     समीक्षाओं
    0.57
     تانيه
    0.54
    criture
    0.51
     tillbaka
    0.50
     Racing
    0.49
     volna
    0.49
     hjälpa
    0.49
     consommateurs
    0.49
     vandens
    0.48
    Activations Density 0.618%

    No Known Activations