© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4617
    Prev
    Next
    INDEX
    Explanations

    language related to sports games and tournaments

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "beat"

    np_token-act-pair-logits · gpt-4o-mini

    beating

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     Efq
    -0.96
     myſelf
    -0.94
     itſelf
    -0.93
     pleaſure
    -0.88
    +#+#
    -0.86
     Monfieur
    -0.85
     doubtnut
    -0.84
     purpoſe
    -0.84
     tfsi
    -0.83
     ་་
    -0.82
    POSITIVE LOGITS
     beat
    0.81
    beat
    0.65
     beats
    0.59
     Beat
    0.56
     f
    0.54
     BEAT
    0.54
     fell
    0.53
     won
    0.53
     fal
    0.52
     beating
    0.52
    Activations Density 1.505%

    No Known Activations