© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3318
    Prev
    Next
    INDEX
    Explanations

    substrings of non-English code with the characters "vr", "po", "is", "es", "di", "ni" or "no"

    oai_token-act-pair · gemini-2.0-flash

    vr

    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
    ConstraintMaker
    -0.70
     createSlice
    -0.65
    antaranya
    -0.55
    newswire
    -0.54
    ikkert
    -0.53
    mphony
    -0.52
    lacian
    -0.52
     bites
    -0.51
    ర్య
    -0.50
     ecológica
    -0.50
    POSITIVE LOGITS
    Fns
    0.59
    TagMode
    0.57
     kasarigan
    0.55
    styleUrls
    0.52
    inheritdoc
    0.51
    InitStruct
    0.50
    GEBURTSDATUM
    0.48
    filé
    0.48
     onCreate
    0.48
    httphttps
    0.47
    Activations Density 5.159%

    No Known Activations