© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6709
    Prev
    Next
    INDEX
    Explanations

    words related to knowing a state, level, or how much you know

    oai_token-act-pair · gemini-2.0-flash

    conditions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    where
    -0.92
     
    -0.79
     where
    -0.78
    .
    -0.70
    Where
    -0.68
    ↵↵
    -0.67
    that
    -0.67
     the
    -0.64
    <eos>
    -0.63
     a
    -0.62
    POSITIVE LOGITS
     للمعارف
    1.31
     المعيارى
    1.26
     للاسماء
    1.25
     مرئيه
    1.23
     Normdatei
    1.22
     utafitiHapana
    1.21
     otomatig
    1.20
    expandindo
    1.17
    новниш
    1.16
    UrlResolution
    1.14
    Activations Density 0.900%

    No Known Activations