© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9603
    Prev
    Next
    INDEX
    Explanations

    mentions of a central location serving as a center of activity

    oai_token-act-pair · gemini-2.0-flash

    hub

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    cos
    -0.63
    Hub
    -0.63
     hub
    -0.60
     inf
    -0.59
     cos
    -0.59
     theirs
    -0.58
    hub
    -0.56
     Hub
    -0.54
     hubs
    -0.54
     ours
    -0.53
    POSITIVE LOGITS
     propOrder
    0.98
    msgTypes
    0.81
    andExpect
    0.81
    WebVitals
    0.81
    WriteBarrier
    0.81
    Aiheesta
    0.77
    XMLSchema
    0.76
    RetentionPolicy
    0.76
    Eloquent
    0.74
    FieldBuilder
    0.71
    Activations Density 1.805%

    No Known Activations