© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5728
    Prev
    Next
    INDEX
    Explanations

    words and strings related to communication, legal agreements and privacy in a non-English language, possibly Serbian or Croatian

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    FieldBuilder
    -0.46
    featureID
    -0.45
     suivantes
    -0.43
     mergeFrom
    -0.43
    المشاركات
    -0.42
    HandlerContext
    -0.41
    άνει
    -0.41
    Autoritní
    -0.41
    setDo
    -0.40
     spela
    -0.40
    POSITIVE LOGITS
    ########.
    0.73
    GraphicsUnit
    0.72
     StatelessWidget
    0.61
    Ik
    0.59
    itext
    0.58
    defer
    0.57
    LLocation
    0.57
     Chines
    0.57
    urator
    0.57
     Receiver
    0.56
    Activations Density 0.134%

    No Known Activations