© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4891
    Prev
    Next
    INDEX
    Explanations

    domain-specific terminology from scientific papers

    oai_token-act-pair · gemini-2.0-flash

    scientific terminology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    })(\
    -0.54
    *)(
    -0.54
    нос
    -0.44
    od
    -0.44
    <bos>
    -0.43
     "./
    -0.43
    alignSelf
    -0.43
    |+\
    -0.42
    fun
    -0.42
    ↵↵
    -0.41
    POSITIVE LOGITS
     متعلقه
    0.98
    LookAnd
    0.84
    verwijspagina
    0.82
     HasFactory
    0.72
     estimés
    0.71
    </tfoot>
    0.69
     Italijanski
    0.67
    #+#
    0.67
    脚注の使い方
    0.66
    endphp
    0.65
    Activations Density 5.591%

    No Known Activations