© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11894
    Prev
    Next
    INDEX
    Explanations

    a jumbled mix of words and phrases around the topics of war, finance, aging, genetic mutation, and disease with no clear overall theme

    oai_token-act-pair · gemini-2.0-flash

    Words with suffixes

    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
    <bos>
    -0.59
     into
    -0.52
     onto
    -0.49
     early
    -0.47
    AlterField
    -0.44
    early
    -0.43
     Ceramby
    -0.43
     start
    -0.42
     đâu
    -0.42
    Into
    -0.41
    POSITIVE LOGITS
    aarrggbb
    0.82
    AndEndTag
    0.69
    parsedMessage
    0.68
    
    0.68
    CppMethod
    0.68
    PerformLayout
    0.67
    SourceChecksum
    0.65
     فريبيس
    0.64
    ftagPool
    0.64
    waltung
    0.60
    Activations Density 6.961%

    No Known Activations