© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 452
    Prev
    Next
    INDEX
    Explanations

    the word 'with', often in the context of living arrangements or close relationships

    oai_token-act-pair · gemini-2.0-flash

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     GenerationType
    -0.71
    GeneratedCode
    -0.71
     createState
    -0.60
    <bos>
    -0.59
    Autoritní
    -0.56
    UnknownFieldSet
    -0.55
    });*/
    -0.53
    enumi
    -0.51
    randomUUID
    -0.50
    })$}
    -0.49
    POSITIVE LOGITS
    BufferException
    0.56
     Frames
    0.55
    ghty
    0.54
     userService
    0.54
     Puls
    0.54
     UITableView
    0.52
     Ludo
    0.51
     ơi
    0.50
     professionale
    0.49
     Barbour
    0.49
    Activations Density 8.343%

    No Known Activations