© 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. 4427
    Prev
    Next
    INDEX
    Explanations

    questions or uncertainty, especially using the word "who"

    oai_token-act-pair · gemini-2.0-flash

    who

    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>
    -1.75
    Who
    -1.34
     Who
    -1.18
    who
    -1.16
     who
    -0.94
    WHO
    -0.94
     WHO
    -0.84
    Кто
    -0.78
     quien
    -0.76
     Кто
    -0.75
    POSITIVE LOGITS
    swell
    0.55
    ogast
    0.53
     convertView
    0.52
    stdc
    0.52
    atzes
    0.52
     Yên
    0.50
    ãng
    0.48
    ousand
    0.48
    edback
    0.48
    perl
    0.47
    Activations Density 2.254%

    No Known Activations