© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2845
    Prev
    Next
    INDEX
    Explanations

    words or phrases that indicate importance or necessity

    oai_token-act-pair · gemini-2.0-flash

    "so" in other 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_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     mxArray
    -0.69
     تانيه
    -0.68
     Pourtant
    -0.68
    DrawerToggle
    -0.64
    цездатний
    -0.60
    brainly
    -0.59
    Javadoc
    -0.59
     unknownFields
    -0.58
     Administrativna
    -0.58
    ('/:
    -0.57
    POSITIVE LOGITS
     so
    2.47
    so
    1.81
     så
    1.58
     zodat
    1.55
    So
    1.47
     So
    1.45
     так
    1.28
     così
    1.28
     כך
    1.20
     sehingga
    1.19
    Activations Density 4.587%

    No Known Activations