© 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. 9576
    Prev
    Next
    INDEX
    Explanations

    numbers with decimal points

    oai_token-act-pair · gemini-2.0-flash

    Non-natural language text

    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
    SPATH
    -0.71
     beginnetje
    -0.65
     mergeFrom
    -0.63
     VIAF
    -0.62
    contentLoaded
    -0.60
    fillType
    -0.59
    InjectAttribute
    -0.59
     propOrder
    -0.59
    انجليز
    -0.56
    NameInMap
    -0.56
    POSITIVE LOGITS
     Mai
    0.56
    KommentareTeilen
    0.54
    OfClass
    0.48
    nutie
    0.48
    ביוגרפיה
    0.47
    MENAFN
    0.46
    żesz
    0.46
     Juli
    0.42
    ativ
    0.42
     Waltz
    0.42
    Activations Density 0.699%

    No Known Activations