© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3757
    Prev
    Next
    INDEX
    Explanations

    negations and conditional statements

    oai_token-act-pair · gemini-2.0-flash

    say "only"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     sole
    -1.59
     solely
    -1.51
    ONLY
    -1.39
     merely
    -1.37
    sole
    -1.36
     ONLY
    -1.34
     Sole
    -1.34
    Sole
    -1.31
     Only
    -1.30
     SOLE
    -1.30
    POSITIVE LOGITS
    complexType
    0.53
    #!/
    0.45
    moduleId
    0.41
     ous
    0.39
    baomidou
    0.39
     iba
    0.38
    Билгалдахарш
    0.38
    rungsseite
    0.38
     len
    0.38
    ilber
    0.38
    Activations Density 3.294%

    No Known Activations