© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3929
    Prev
    Next
    INDEX
    Explanations

    words used to describe moral actions and legal consequences

    oai_token-act-pair · gemini-2.0-flash

    negative situations and bravery

    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
    chyma
    -0.49
     meubles
    -0.45
     Federal
    -0.40
    гор
    -0.40
     ilmo
    -0.39
    qualification
    -0.39
    ejs
    -0.39
    ::_('
    -0.38
     Others
    -0.38
    $<$
    -0.37
    POSITIVE LOGITS
    Personensuche
    0.91
    تقاوى
    0.90
    TintMode
    0.72
    SourceChecksum
    0.70
     nahilalakip
    0.70
     المعيارى
    0.68
    parsedMessage
    0.68
    yled
    0.68
     cherchés
    0.68
     समीक्षाओं
    0.67
    Activations Density 33.347%

    No Known Activations