© 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. 7601
    Prev
    Next
    INDEX
    Explanations

    past tense verbs related to witnessing or physical actions, often suggestive of a narrative

    oai_token-act-pair · gemini-2.0-flash

    People

    np_max-act-logits · gemini-2.0-flash

    people

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    awtextra
    -0.58
    ifo
    -0.57
     Proz
    -0.56
    +#+
    -0.54
     transférez
    -0.54
     Lichten
    -0.54
     cruz
    -0.50
    hetically
    -0.49
    శ
    -0.49
    реи
    -0.48
    POSITIVE LOGITS
     initComponents
    0.56
     been
    0.55
    been
    0.52
    useNewUrlParser
    0.50
     francès
    0.50
    engertian
    0.50
    stęp
    0.48
    kmale
    0.47
     být
    0.47
     terdekat
    0.47
    Activations Density 35.985%

    No Known Activations