© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11588
    Prev
    Next
    INDEX
    Explanations

    language that uses terms of endearment and positive reinforcement

    oai_token-act-pair · gemini-2.0-flash

    so

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    MemoryWarning
    -0.82
    UrlResolution
    -0.76
    ENSIS
    -0.72
     للاسماء
    -0.69
     Normdatei
    -0.69
     تضيفلها
    -0.67
     विश्वसनीयता
    -0.66
     Theſe
    -0.65
    存于互联网档案馆
    -0.65
    IVEREF
    -0.64
    POSITIVE LOGITS
     so
    3.38
    so
    2.52
    So
    2.25
     SO
    2.16
     So
    2.16
     så
    1.96
     soo
    1.70
    SO
    1.67
    如此
    1.66
     так
    1.65
    Activations Density 2.046%

    No Known Activations