© 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. 3893
    Prev
    Next
    INDEX
    Explanations

    text segments describing or related to contests or raffle in exchange for something, in this case filling out a survey

    oai_token-act-pair · gemini-2.0-flash

    Contests and winning

    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
    énario
    -0.75
    awtextra
    -0.73
    Personendaten
    -0.65
    fromnode
    -0.63
    mergeFrom
    -0.63
    IsMutable
    -0.60
    ByVersion
    -0.60
    BASEPATH
    -0.60
    ForValue
    -0.59
     EClass
    -0.58
    POSITIVE LOGITS
     won
    0.56
    won
    0.52
     Won
    0.51
     WON
    0.51
     Airs
    0.49
    WON
    0.48
    woon
    0.48
     pengh
    0.48
    ()}}
    0.47
    ungalows
    0.47
    Activations Density 5.468%

    No Known Activations