© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11851
    Prev
    Next
    INDEX
    Explanations

    words that intensify the rest of the sentence

    oai_token-act-pair · gemini-2.0-flash

    particularly/especially

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     autorytatywna
    -0.91
     Majefty
    -0.76
    ſelves
    -0.74
     kaarangay
    -0.74
    ſelf
    -0.73
     ModelExpression
    -0.71
    })`
    -0.71
    webElementGuid
    -0.71
    Portály
    -0.71
     ſind
    -0.70
    POSITIVE LOGITS
     those
    0.65
    those
    0.59
    Those
    0.55
     celles
    0.55
     ceux
    0.54
     Those
    0.52
     since
    0.50
     kerana
    0.50
     THOSE
    0.50
     jene
    0.48
    Activations Density 3.114%

    No Known Activations