© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3594
    Prev
    Next
    INDEX
    Explanations

    the word "whose," and sometimes "her/or"

    oai_token-act-pair · gemini-2.0-flash

    whose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     BaseModel
    -0.71
     Normdatei
    -0.71
    Obrázky
    -0.70
    مقاله
    -0.66
    DockStyle
    -0.66
    ">—
    -0.65
    onomía
    -0.64
    SpringRunner
    -0.64
    endphp
    -0.63
     ddelweddau
    -0.63
    POSITIVE LOGITS
     own
    0.95
     seu
    0.69
    own
    0.65
    Own
    0.65
     kendi
    0.64
     suo
    0.63
     suoi
    0.63
     vostro
    0.62
     Its
    0.62
     Ihre
    0.61
    Activations Density 0.936%

    No Known Activations