© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4828
    Prev
    Next
    INDEX
    Explanations

    words associated with making observations and reporting findings

    oai_token-act-pair · gemini-2.0-flash

    indicate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -2.06
     indicate
    -0.91
     indicates
    -0.85
     suggest
    -0.71
     suggests
    -0.70
    indicate
    -0.64
     reflect
    -0.63
     imply
    -0.61
    indicates
    -0.61
    '
    -0.61
    POSITIVE LOGITS
     MainAxisSize
    0.67
    principalTable
    0.67
    ̍t
    0.66
    :✨
    0.65
     getSub
    0.65
    Зміст
    0.64
    colony
    0.64
    Datuak
    0.63
    ghold
    0.63
     Stretcher
    0.62
    Activations Density 6.508%

    No Known Activations