© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3515
    Prev
    Next
    INDEX
    Explanations

    words related to the Japanese show "One Piece" and the phrase "voiced by".

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Monfieur
    -0.62
     retraite
    -0.56
     invokingState
    -0.55
     Gaylord
    -0.54
    archiviato
    -0.52
     Infórmanos
    -0.52
    packung
    -0.51
     plastique
    -0.51
     contrats
    -0.50
     Theſe
    -0.50
    POSITIVE LOGITS
     ModelExpression
    0.63
    ollectionView
    0.55
     jScrollPane
    0.55
     CWE
    0.54
    Anhalt
    0.52
    Бахар
    0.52
    IntoConstraints
    0.52
    PositiveButton
    0.51
    ellido
    0.50
    UserController
    0.50
    Activations Density 1.506%

    No Known Activations