© 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. 13585
    Prev
    Next
    INDEX
    Explanations

    product dimensions and related marketing phrases

    oai_token-act-pair · gemini-2.0-flash

    1

    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
    Negative Logits
     INTERESAR
    -0.58
    <bos>
    -0.52
     lettore
    -0.48
    Diwedd
    -0.47
     Trouver
    -0.45
    TagHelper
    -0.44
     recortes
    -0.44
    MIDDLEWARE
    -0.43
     miss
    -0.43
    Drying
    -0.43
    POSITIVE LOGITS
    LLocation
    0.67
    onViewCreated
    0.66
     виправивши
    0.65
    ThroughAttribute
    0.64
    قایناق‌لار
    0.61
     lenker
    0.59
    DockStyle
    0.58
    KNOWN
    0.57
    modelBuilder
    0.56
    <?
    0.56
    Activations Density 2.837%

    No Known Activations