© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13316
    Prev
    Next
    INDEX
    Explanations

    words related to legal compliance and publication, particularly in the scientific domain.

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     this
    -0.88
     there
    -0.80
     the
    -0.73
     these
    -0.68
     they
    -0.65
     in
    -0.59
    ".
    -0.58
     as
    -0.54
     you
    -0.54
     their
    -0.54
    POSITIVE LOGITS
     Wherefore
    0.89
    HtmlAttribute
    0.84
     démocr
    0.80
     Commonly
    0.80
     Gonna
    0.80
    So
    0.77
     Biggest
    0.77
     Primarily
    0.76
     Optimize
    0.76
     Manually
    0.75
    Activations Density 8.979%

    No Known Activations