© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13130
    Prev
    Next
    INDEX
    Explanations

    words or phrases which have positive associations or relate to authority

    oai_token-act-pair · gemini-2.0-flash

    full/packed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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>
    -0.72
     amitié
    -0.56
     decorativos
    -0.56
     marié
    -0.54
     measles
    -0.51
     geométrico
    -0.51
     chapels
    -0.51
     scania
    -0.51
     dõi
    -0.50
     decorativa
    -0.50
    POSITIVE LOGITS
     EconPapers
    0.71
    culable
    0.69
    yntaxException
    0.68
    Ahem
    0.68
    memoized
    0.68
    tanleria
    0.66
     समीक्षक
    0.65
    ADELPHIA
    0.65
    ordinaire
    0.64
    úrate
    0.64
    Activations Density 2.123%

    No Known Activations