© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6161
    Prev
    Next
    INDEX
    Explanations

    mentions of somebody speaking

    oai_token-act-pair · gemini-2.0-flash

    Saying/whispering

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    sih
    -0.46
    火
    -0.42
    fii
    -0.41
    гли
    -0.39
    ви
    -0.39
    Fiche
    -0.39
    BarStyle
    -0.39
    ity
    -0.38
     Ata
    -0.38
    拿起
    -0.38
    POSITIVE LOGITS
     whispering
    0.94
     muttering
    0.87
    saying
    0.86
    SourceChecksum
    0.86
    :✨
    0.85
     whisper
    0.84
     Saying
    0.82
     saying
    0.82
     conversations
    0.81
    expandindo
    0.80
    Activations Density 0.771%

    No Known Activations