© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12317
    Prev
    Next
    INDEX
    Explanations

    instances of technical writing, using surrounding punctuation and sentence fragments as clues within the document

    oai_token-act-pair · gemini-2.0-flash

    period

    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
    เหล
    -0.57
     quei
    -0.47
    它们
    -0.47
     esos
    -0.45
     وہ
    -0.45
    它們
    -0.44
    ErrUnexpectedEOF
    -0.41
     These
    -0.41
    这些
    -0.39
     esas
    -0.38
    POSITIVE LOGITS
     this
    2.92
    this
    2.52
    This
    1.95
     This
    1.84
     THIS
    1.83
     questo
    1.68
    THIS
    1.66
     questa
    1.61
     этого
    1.55
     dieses
    1.52
    Activations Density 5.258%

    No Known Activations