© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13596
    Prev
    Next
    INDEX
    Explanations

    verbs related to questioning and eliciting information.

    oai_token-act-pair · gemini-2.0-flash

    legal/interview contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     RSSSF
    -0.64
     itſelf
    -0.63
    ưới
    -0.63
     auffi
    -0.61
    '},
    -0.61
    )"),
    -0.60
     Efq
    -0.60
    $")
    -0.60
     ویکی‌پدیای
    -0.60
    lepiej
    -0.59
    POSITIVE LOGITS
    :✨
    0.71
    ScopeManager
    0.63
     оригіналу
    0.58
    DeleteBehavior
    0.58
     सत्यापित
    0.57
     induced
    0.56
     induce
    0.55
    wingen
    0.54
     Induced
    0.52
    Abit
    0.50
    Activations Density 3.202%

    No Known Activations