© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 407
    Prev
    Next
    INDEX
    Explanations

    words in Croatian related to Facebook's terms of service and data usage policies

    oai_token-act-pair · gemini-2.0-flash

    Interjection "um" or "uh"

    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
     ale
    -0.60
    endphp
    -0.55
     Dropout
    -0.53
     ales
    -0.53
     DbContext
    -0.52
    Ale
    -0.52
    ijnt
    -0.52
    menes
    -0.52
     Ale
    -0.51
    Aber
    -0.50
    POSITIVE LOGITS
     um
    1.13
     Um
    0.89
     uh
    0.85
    Um
    0.76
     umm
    0.66
     UM
    0.65
     Uh
    0.64
    :✨
    0.61
    um
    0.60
    Uh
    0.59
    Activations Density 0.684%

    No Known Activations