© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8183
    Prev
    Next
    INDEX
    Explanations

    words and phrases containing "ass" that are not "glass"

    oai_token-act-pair · gemini-2.0-flash

    ass

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     feroit
    -0.62
    ed
    -0.61
     auroit
    -0.60
     acrylique
    -0.56
    empereur
    -0.56
    extérieur
    -0.55
     vostri
    -0.53
     espagne
    -0.53
     dévelo
    -0.52
     clô
    -0.52
    POSITIVE LOGITS
    omeness
    0.60
    hip
    0.60
    teel
    0.60
    hares
    0.56
     незавершена
    0.56
    itinéraire
    0.56
    hes
    0.56
    heet
    0.55
    بوابة
    0.54
    uite
    0.54
    Activations Density 8.252%

    No Known Activations