© 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. 8263
    Prev
    Next
    INDEX
    Explanations

    words related to modifying software or fixing errors, especially patches

    oai_token-act-pair · gemini-2.0-flash

    Software patches and hacks

    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
    Hack
    -2.02
     hack
    -2.02
     patch
    -1.98
     Hack
    -1.97
     Patch
    -1.91
     hacking
    -1.84
     HACK
    -1.83
    Patch
    -1.81
    patch
    -1.80
     hacked
    -1.77
    POSITIVE LOGITS
    setVerticalGroup
    0.57
    AxisAlignment
    0.56
     DN
    0.55
    DoubleQuotes
    0.54
     trânsito
    0.50
     الدولى
    0.49
    ammlung
    0.47
     BoxFit
    0.47
     Purcell
    0.47
     Kelvin
    0.46
    Activations Density 1.817%

    No Known Activations