© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6700
    Prev
    Next
    INDEX
    Explanations

    different tenses of the verb "to be," with a bias towards recognizing non-English versions.

    oai_token-act-pair · gemini-2.0-flash

    online chatMethod: 2, reason: TOP_ACTIVATING_TEXTS contain chat-like text, often including other languages.online chat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    OGND
    -0.73
     ComVisible
    -0.70
     ProtoMessage
    -0.69
    الحياه
    -0.68
     Chwiliwch
    -0.67
    WebElementEntity
    -0.64
     crescere
    -0.61
     convergence
    -0.60
     AssemblyCulture
    -0.60
    rungsseite
    -0.59
    POSITIVE LOGITS
     was
    0.56
     had
    0.54
     been
    0.49
     would
    0.48
    was
    0.48
    would
    0.47
     Had
    0.47
     serait
    0.47
    Had
    0.46
     be
    0.46
    Activations Density 0.711%

    No Known Activations