© 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. 11568
    Prev
    Next
    INDEX
    Explanations

    parts of build scripts with sed commands, some words in Croatian, and some terms related to semiconductors

    oai_token-act-pair · gemini-2.0-flash

    Code/Foreign languages

    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
    sa
    -0.97
    za
    -0.95
    ka
    -0.94
    ita
    -0.90
    ina
    -0.89
    ZA
    -0.88
    SA
    -0.86
    ICA
    -0.86
    ika
    -0.86
    CHA
    -0.85
    POSITIVE LOGITS
    PRNewswire
    0.60
     دیکھیے
    0.56
    GEBURTSDATUM
    0.53
    addGap
    0.53
    цездатний
    0.52
    !*\
    0.49
     المعيارى
    0.49
    HomeAsUpEnabled
    0.48
     kaarangay
    0.47
    Personendaten
    0.47
    Activations Density 4.811%

    No Known Activations