© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9850
    Prev
    Next
    INDEX
    Explanations

    questions using words like who, where, why, or what, or words related to truth and judgment.

    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_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     who
    -0.74
    Who
    -0.71
     Who
    -0.69
     hvem
    -0.64
    OrBuilder
    -0.64
     Siapa
    -0.63
    IconModule
    -0.63
    who
    -0.62
     quién
    -0.60
    PathVariable
    -0.59
    POSITIVE LOGITS
     Wiktionnaire
    0.54
     Tym
    0.54
    anglès
    0.53
    hunt
    0.52
     Crate
    0.50
     lumineuse
    0.47
     régulier
    0.47
    通用
    0.47
     Sensory
    0.47
     hubby
    0.47
    Activations Density 16.639%

    No Known Activations