© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7176
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers and machine instructions

    oai_token-act-pair · gemini-2.0-flash

    6

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <eos>
    -0.50
     
    -0.44
    ён
    -0.44
     baz
    -0.42
    !
    -0.39
     независи
    -0.39
    渠
    -0.39
    .
    -0.38
    يار
    -0.38
    ram
    -0.38
    POSITIVE LOGITS
     ModelExpression
    1.16
    Personensuche
    1.00
     propOrder
    0.99
    CloseOperation
    0.99
    CodedInputStream
    0.98
     nakalista
    0.97
    Geplaatst
    0.96
    AsUp
    0.94
     незавершена
    0.92
    المناصب
    0.92
    Activations Density 0.258%

    No Known Activations