© 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. 14122
    Prev
    Next
    INDEX
    Explanations

    scientific or medical notation abbreviations or acronyms

    oai_token-act-pair · gemini-2.0-flash

    Biology-related abbreviations

    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
    ArgsConstructor
    -0.43
    Glej
    -0.40
     Winaray
    -0.40
    ImageField
    -0.40
    fjspx
    -0.36
    hiasan
    -0.36
     estimés
    -0.36
    multer
    -0.35
    ✭✭
    -0.35
    tahankan
    -0.35
    POSITIVE LOGITS
    bos
    0.84
     BA
    0.84
     BT
    0.83
     BL
    0.82
     BB
    0.82
     BP
    0.82
     BOS
    0.81
     Boron
    0.81
     BK
    0.81
     BN
    0.81
    Activations Density 14.269%

    No Known Activations