© 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. 12055
    Prev
    Next
    INDEX
    Explanations

    the word "under" and sometimes finds the words "we" or "or"

    oai_token-act-pair · gemini-2.0-flash

    under

    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
     under
    -0.96
     Bourgoin
    -0.81
    drawal
    -0.79
    URLException
    -0.75
    ivity
    -0.72
    ratulations
    -0.72
    ieval
    -0.72
    PyExc
    -0.70
     past
    -0.70
    fflush
    -0.70
    POSITIVE LOGITS
     gouvernements
    0.76
     pattes
    0.75
     larmes
    0.75
     feroit
    0.73
     nemici
    0.72
     esclavos
    0.72
     boî
    0.71
     travailleurs
    0.71
     étoient
    0.68
     pouvoirs
    0.68
    Activations Density 4.226%

    No Known Activations