© 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. 4954
    Prev
    Next
    INDEX
    Explanations

    positive adjectives near the word "good."

    oai_token-act-pair · gemini-2.0-flash

    good

    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
    ್
    -0.53
    OGND
    -0.46
    zt
    -0.46
    cedent
    -0.44
    LIKE
    -0.43
    yk
    -0.43
    ztat
    -0.42
     like
    -0.41
    waitKey
    -0.41
     Tapatalk
    -0.41
    POSITIVE LOGITS
     myſelf
    0.69
     itſelf
    0.67
     nahilalakip
    0.67
     Monfieur
    0.65
     themſelves
    0.63
     useNavigate
    0.63
     snippetHide
    0.63
     againſt
    0.63
     &___
    0.63
     uſed
    0.62
    Activations Density 3.738%

    No Known Activations