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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9010
    Prev
    Next
    INDEX
    Explanations

    words strongly associated with live entertainment events, especially concerts and tours

    oai_token-act-pair · gemini-2.0-flash

    Concerts and tours

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     perform
    -0.62
    Perform
    -0.56
     الحره
    -0.55
     performing
    -0.55
     performs
    -0.53
     Perform
    -0.52
    irmar
    -0.50
    perform
    -0.49
     Cached
    -0.49
     Noten
    -0.48
    POSITIVE LOGITS
    ymce
    0.81
    IsMutable
    0.66
     ExecuteAsync
    0.65
     Signalez
    0.64
     AssemblyTitle
    0.63
     defaultstate
    0.62
    ValueStyle
    0.60
    ExtendWith
    0.59
    awtextra
    0.58
     OFDb
    0.56
    Activations Density 3.237%

    No Known Activations