© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12619
    Prev
    Next
    INDEX
    Explanations

    addresses containing numbers and building names, usually formatted for Germany and/or Italy

    oai_token-act-pair · gemini-2.0-flash

    Addresses in academic publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     miss
    -0.49
    —
    -0.45
    териалы
    -0.44
     misses
    -0.43
     turn
    -0.42
    -0.42
    Missed
    -0.41
    Abs
    -0.41
    strafe
    -0.41
     err
    -0.40
    POSITIVE LOGITS
     للمعارف
    1.11
    UnsafeEnabled
    0.95
     cherchés
    0.93
    +#+#
    0.91
    parsedMessage
    0.91
     Roskov
    0.90
    клопе
    0.89
     protoimpl
    0.88
    !*\
    0.87
    Бахар
    0.87
    Activations Density 0.407%
    No Known Activations