© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13208
    Prev
    Next
    INDEX
    Explanations

    mentions of the United Nations (UN) and related terminology and also appears to potentially activate on dates with only a fraction of the response strength

    oai_token-act-pair · gemini-2.0-flash

    United Nations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    IVEREF
    -0.60
     UN
    -0.48
     roll
    -0.45
    blond
    -0.43
     opener
    -0.42
    ynos
    -0.42
     nén
    -0.41
    ]]]
    -0.41
     الرياضيه
    -0.41
    transQ
    -0.40
    POSITIVE LOGITS
     kasarigan
    0.68
     Roskov
    0.63
    sidemargin
    0.63
    PullParser
    0.61
    зулта
    0.60
    GEBURTSDATUM
    0.60
    TagHelper
    0.57
    KommentareTeilen
    0.57
    سمبر
    0.56
     Waray
    0.56
    Activations Density 0.840%

    No Known Activations