© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4953
    Prev
    Next
    INDEX
    Explanations

    sentences about financial impropriety or taxes

    oai_token-act-pair · gemini-2.0-flash

    business and entrepreneurs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     quæ
    -0.59
     distanciation
    -0.52
     avoient
    -0.49
    colorPrimary
    -0.49
    unconfirmed
    -0.48
    igation
    -0.48
     fufficient
    -0.47
    StoreMessageInfo
    -0.47
    vernight
    -0.47
     setter
    -0.46
    POSITIVE LOGITS
    tagHelperRunner
    0.69
    httphttps
    0.66
    apimachinery
    0.65
     समीक्षाएं
    0.63
    SequentialGroup
    0.57
    ագրություններ
    0.56
    Cyfeiriadau
    0.54
    AnchorStyles
    0.54
     defaultstate
    0.54
    DotNetBar
    0.54
    Activations Density 8.597%

    No Known Activations