© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12347
    Prev
    Next
    INDEX
    Explanations

    the word "play" but it also seems to be partially activated by the word "copy".

    oai_token-act-pair · gemini-2.0-flash

    play

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    XmlAccessorType
    -0.69
     оригіналу
    -0.65
    WindowConstants
    -0.61
    URLException
    -0.61
     Slu
    -0.59
    BagLayout
    -0.58
    InstanceState
    -0.57
    waltung
    -0.56
    ROIT
    -0.56
    iclo
    -0.56
    POSITIVE LOGITS
     Familienname
    0.48
    UrlResolution
    0.48
    angliski
    0.47
     agrí
    0.46
    NameInMap
    0.45
    /*:
    0.42
    !*\
    0.42
     specie
    0.42
    Disposition
    0.41
    Datuak
    0.40
    Activations Density 0.541%

    No Known Activations