© 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. 15483
    Prev
    Next
    INDEX
    Explanations

    the word "software."

    oai_token-act-pair · gemini-2.0-flash

    software

    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
     يتيمه
    -0.88
     crdi
    -0.88
    saraba
    -0.88
     Efq
    -0.87
    رشف
    -0.85
    windowFixed
    -0.82
    Cordialement
    -0.79
     خارجية
    -0.79
     Chwiliwch
    -0.79
     grecque
    -0.78
    POSITIVE LOGITS
    a
    0.67
    ι
    0.60
    adel
    0.60
    e
    0.59
    ah
    0.57
    <i>
    0.57
     
    0.57
    ta
    0.55
    ا
    0.55
    an
    0.55
    Activations Density 0.640%

    No Known Activations