© 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. 5107
    Prev
    Next
    INDEX
    Explanations

    tentative or conversational phrases and interjections at the start of sentences, and terms related to evaluating an ongoing situation

    oai_token-act-pair · gemini-2.0-flash

    Well

    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
    Well
    -0.87
     well
    -0.85
    well
    -0.80
     Well
    -0.79
    WELL
    -0.72
     bien
    -0.69
    wells
    -0.68
     WELL
    -0.65
     bem
    -0.57
     BIEN
    -0.55
    POSITIVE LOGITS
    shot
    0.65
     Shakspeare
    0.60
     observed
    0.60
     picked
    0.60
     shot
    0.59
     visited
    0.57
     sucked
    0.57
     informed
    0.57
     jerked
    0.57
     watched
    0.56
    Activations Density 10.041%

    No Known Activations