© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13546
    Prev
    Next
    INDEX
    Explanations

    descriptions of how someone speaks, plus related negative sentiments and people speaking quietly

    oai_token-act-pair · gemini-2.0-flash

    accent/voice/sense

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    MLLoader
    -0.85
     Exacts
    -0.61
     doInBackground
    -0.60
    mybatisplus
    -0.60
     transfieras
    -0.53
     Exactos
    -0.53
    ClientSize
    -0.53
    ParallelGroup
    -0.51
    GEBURTSDATUM
    -0.50
    SPATH
    -0.50
    POSITIVE LOGITS
     sense
    0.66
    ONTO
    0.55
     Sense
    0.54
    soort
    0.54
    eckel
    0.52
    κτηρισ
    0.52
    )++;
    0.52
    <?
    0.50
     CWE
    0.50
    Sense
    0.49
    Activations Density 0.677%

    No Known Activations