© 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. 3279
    Prev
    Next
    INDEX
    Explanations

    words and short phrases common to scientific publications that provide context and refer to things like panels, studies, and selections from publications

    oai_token-act-pair · gemini-2.0-flash

    over

    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
    nine
    -0.71
    Nine
    -0.70
     Nearly
    -0.70
    Nearly
    -0.69
     hundred
    -0.68
     dozen
    -0.67
    Thirteen
    -0.67
    Twenty
    -0.66
    Eight
    -0.66
    Thirty
    -0.66
    POSITIVE LOGITS
     
    1.70
     over
    1.52
     Over
    1.08
    Over
    1.05
     OVER
    1.02
    over
    1.02
     över
    0.94
     über
    0.85
     sobre
    0.83
    OVER
    0.82
    Activations Density 9.208%

    No Known Activations