© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16086
    Prev
    Next
    INDEX
    Explanations

    sentences that contain uncertainty or conditions, often using words like 'if,' 'probably,' or 'may.'

    oai_token-act-pair · gemini-2.0-flash

    won

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    曖昧さ回避
    -0.50
    тие
    -0.47
    舞
    -0.42
    msch
    -0.42
    >//
    -0.42
    etzten
    -0.40
    Rosen
    -0.40
    زاد
    -0.40
    ف
    -0.40
    pagestyle
    -0.39
    POSITIVE LOGITS
     won
    2.83
    Won
    2.52
    won
    2.48
     Won
    2.42
     WON
    2.16
    WON
    1.84
     wont
    1.77
     remporté
    1.17
     vinto
    0.98
    expandindo
    0.93
    Activations Density 4.027%

    No Known Activations