© 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. 6651
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and relative pronouns near verbs of knowing

    oai_token-act-pair · gemini-2.0-flash

    meeting

    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
    ]+"
    -0.58
    ishwa
    -0.53
    ``.
    -0.52
    ";}
    -0.49
     Theses
    -0.48
    pecies
    -0.47
    )\}
    -0.47
    bura
    -0.46
     }}"></
    -0.45
     iç
    -0.45
    POSITIVE LOGITS
     met
    1.09
     meet
    0.99
    meet
    0.95
     conoció
    0.93
     meeting
    0.91
    Meet
    0.90
     познакоми
    0.90
     discovered
    0.89
     bertemu
    0.89
     meets
    0.89
    Activations Density 0.932%

    No Known Activations