© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13639
    Prev
    Next
    INDEX
    Explanations

    quotations/reporting from named sources in media and direct speech

    oai_token-act-pair · gemini-2.0-flash

    writing, wrote, write

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Ahead
    -0.50
    Ahead
    -0.48
     HttpStatusCode
    -0.42
    ígenes
    -0.42
     समीक्षाएं
    -0.42
    भग
    -0.41
     XCTest
    -0.40
    apunov
    -0.40
     ahead
    -0.40
     čin
    -0.40
    POSITIVE LOGITS
     writing
    1.24
     write
    1.23
     wrote
    1.21
     Writing
    1.16
     writes
    1.16
     Wrote
    1.09
     Write
    1.06
     written
    1.05
    Writing
    1.05
    write
    1.03
    Activations Density 2.173%

    No Known Activations