© 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. 9637
    Prev
    Next
    INDEX
    Explanations

    HTML bold tags and words associated with actions and options

    oai_token-act-pair · gemini-2.0-flash

    `<b>`

    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
    <b>
    -1.78
    </b>
    -1.28
    </i>
    -1.12
    dfrac
    -0.88
    :+:
    -0.74
     NgModule
    -0.63
    例文帳に追加
    -0.59
    MigrationBuilder
    -0.58
     + 
    -0.57
    <i>
    -0.56
    POSITIVE LOGITS
     **/
    0.82
    </strong>
    0.79
     
    0.77
     first
    0.70
    ",@"
    0.69
    """.
    0.68
    }}">
    0.68
    "<<
    0.67
     fl
    0.67
    </em>
    0.67
    Activations Density 1.494%

    No Known Activations