© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7122
    Prev
    Next
    INDEX
    Explanations

    articles and prepositions in a short sentence, possibly identifying relationships between nouns and locations

    oai_token-act-pair · gemini-2.0-flash

    location

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Revenir
    -0.57
    seamnă
    -0.56
    LookAnd
    -0.56
     mergeFrom
    -0.54
    IVEREF
    -0.53
    قایناق‌لار
    -0.53
     vicenda
    -0.52
     SEDS
    -0.50
     становника
    -0.50
    MENAFN
    -0.49
    POSITIVE LOGITS
     location
    0.66
     position
    0.64
     lookout
    0.59
     spot
    0.58
    Position
    0.56
     Location
    0.56
     point
    0.54
    ftagPool
    0.52
    position
    0.52
    location
    0.52
    Activations Density 2.658%

    No Known Activations