© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11311
    Prev
    Next
    INDEX
    Explanations

    words related to interpreting, clarifying, illumination, or asserting

    oai_token-act-pair · gemini-2.0-flash

    interpretation, light, religion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     lit
    -0.69
    lit
    -0.56
     rub
    -0.55
     sp
    -0.55
    illoma
    -0.53
     
    -0.53
     exploit
    -0.52
    Sucesor
    -0.52
     Rub
    -0.50
     Lit
    -0.47
    POSITIVE LOGITS
    ArrowToggle
    0.78
     StatelessWidget
    0.77
    énario
    0.76
     kasarigan
    0.75
    tvguidetime
    0.75
    Vidite
    0.74
    ########.
    0.73
    KommentareTeilen
    0.72
     transfieras
    0.72
     PrintWriter
    0.72
    Activations Density 1.249%

    No Known Activations