© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9327
    Prev
    Next
    INDEX
    Explanations

    mentions of Apple operating systems with version numbers

    oai_token-act-pair · gemini-2.0-flash

    MacOS versions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    utuhkan
    -0.62
    ressum
    -0.58
    ilogue
    -0.53
    =|
    -0.51
    PrototypeOf
    -0.50
    Cloning
    -0.49
    endio
    -0.49
    }.
    -0.49
    }])
    -0.48
    ChildScrollView
    -0.47
    POSITIVE LOGITS
    <bos>
    1.03
    SourceChecksum
    0.75
    AddTagHelper
    0.65
    ModelBuilder
    0.62
     استنادى
    0.59
     Administrativna
    0.57
     وتسجيلات
    0.53
     []:
    0.53
    sonaro
    0.52
    tvguidetime
    0.52
    Activations Density 2.296%

    No Known Activations