© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12458
    Prev
    Next
    INDEX
    Explanations

    correlative constructions, especially "as... so..." and phrases about money

    oai_token-act-pair · gemini-2.0-flash

    so

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    DebuggerStep
    -0.58
    onBackPressed
    -0.56
    //});
    -0.51
    ISHED
    -0.46
    providedIn
    -0.44
    oque
    -0.43
    '}}
    -0.42
    setupUi
    -0.42
    <bos>
    -0.42
     कि
    -0.42
    POSITIVE LOGITS
     resourceCulture
    0.73
    ----</
    0.68
     صوتيه
    0.66
    awtextra
    0.64
    ulsions
    0.64
    DoubleQuotes
    0.62
     Roskov
    0.61
    RectangleBorder
    0.59
    BagLayout
    0.58
     wireType
    0.57
    Activations Density 1.071%

    No Known Activations