© 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. 14442
    Prev
    Next
    INDEX
    Explanations

    the word "stop", and sometimes "dog" too

    oai_token-act-pair · gemini-2.0-flash

    stop

    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
    awtextra
    -0.68
     autorytatywna
    -0.68
     Commencez
    -0.63
    <bos>
    -0.62
     للمعارف
    -0.61
     تعدى
    -0.57
    replaceable
    -0.56
    Fitz
    -0.55
    Code
    -0.54
    arlos
    -0.53
    POSITIVE LOGITS
     religieuse
    0.84
     grecque
    0.82
     chrétienne
    0.77
     chrétien
    0.77
     clearColor
    0.73
     Amiens
    0.71
     blanches
    0.69
     japonais
    0.68
    }\]
    0.67
     大全
    0.67
    Activations Density 1.646%

    No Known Activations