© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10567
    Prev
    Next
    INDEX
    Explanations

    a mix of Spanish and Portuguese words related to programming/scripting actions

    oai_token-act-pair · gemini-2.0-flash

    Code and foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     purpoſe
    -0.94
     ſeveral
    -0.86
     Efq
    -0.84
     ſmall
    -0.84
     raiſ
    -0.83
     Theſe
    -0.81
     reaſon
    -0.80
     itſelf
    -0.79
     ſen
    -0.79
     Reſ
    -0.79
    POSITIVE LOGITS
    mobileqq
    0.40
    homonymie
    0.39
     Made
    0.39
     Co
    0.39
    了他
    0.39
    WithIOException
    0.39
    ⊕
    0.38
    OPINION
    0.38
    eeq
    0.38
     de
    0.38
    Activations Density 0.606%

    No Known Activations