© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13237
    Prev
    Next
    INDEX
    Explanations

    the word "Is" followed by a lowercase letter

    oai_token-act-pair · gemini-2.0-flash

    Is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     médicaux
    -0.60
     scolaires
    -0.59
     négociations
    -0.59
     virtuales
    -0.58
     lavoratori
    -0.57
    endphp
    -0.57
     traités
    -0.57
     vocales
    -0.57
    ennemi
    -0.57
     vectorielles
    -0.57
    POSITIVE LOGITS
     ujednoznacz
    0.52
    تقاوى
    0.49
    ỏi
    0.49
    ormány
    0.48
     Responsible
    0.47
    ot
    0.47
     للمعارف
    0.46
    rrggbb
    0.46
    SerializedSize
    0.46
    TypedDataSet
    0.44
    Activations Density 1.264%

    No Known Activations