© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12314
    Prev
    Next
    INDEX
    Explanations

    a mix of Spanish and Portuguese words, especially verbs, related to programming and game-playing

    oai_token-act-pair · gemini-2.0-flash

    Foreign language text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     their
    -0.51
    WithTag
    -0.50
     unirse
    -0.50
    untitled
    -0.49
     utafitiHapana
    -0.49
    互
    -0.49
    pédie
    -0.48
    JoinTable
    -0.48
    DockStyle
    -0.45
     theirs
    -0.45
    POSITIVE LOGITS
     myself
    1.23
     myſelf
    0.96
    myself
    0.91
     Myself
    0.90
    <bos>
    0.82
    endphp
    0.67
    raszam
    0.67
    дарю
    0.65
    felde
    0.63
     ComVisible
    0.63
    Activations Density 0.237%

    No Known Activations