© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9485
    Prev
    Next
    INDEX
    Explanations

    text describing disadvantages and costs of different technical or scientific methods.

    oai_token-act-pair · gemini-2.0-flash

    advantage, disadvantage, cost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.97
    <bos>
    -0.88
    GEBURTSDATUM
    -0.82
    protoimpl
    -0.81
     propOrder
    -0.79
    PerformLayout
    -0.77
    RegressionTest
    -0.76
    सन्दर्भ
    -0.71
    MigrationBuilder
    -0.71
    "]));
    -0.71
    POSITIVE LOGITS
    ʊ
    0.48
    حديد
    0.45
     cost
    0.45
     patrón
    0.45
    ždý
    0.44
     Cost
    0.44
    chell
    0.43
    arate
    0.43
    luo
    0.43
     Mercer
    0.42
    Activations Density 2.663%

    No Known Activations