© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4259
    Prev
    Next
    INDEX
    Explanations

    certain legal, technical, or statistical jargon is used

    oai_token-act-pair · gemini-2.0-flash

    Formal texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Schme
    -0.48
     Sigism
    -0.47
     Athene
    -0.47
     mutton
    -0.47
     TypeError
    -0.46
     Parisi
    -0.46
     Mussolini
    -0.45
     Chilean
    -0.45
     Mme
    -0.44
     Panchayat
    -0.44
    POSITIVE LOGITS
     EconPapers
    0.84
    rungsseite
    0.78
     Wikimedijinoj
    0.77
    قایناق‌لار
    0.70
     ujednoznacz
    0.66
    windowFixed
    0.66
    Халык
    0.64
    ----</
    0.63
    PerformLayout
    0.60
    +)/
    0.60
    Activations Density 9.425%

    No Known Activations