© 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. 4169
    Prev
    Next
    INDEX
    Explanations

    words related to various, somewhat vague, technical problems or writing snippets (such as with Android development).

    oai_token-act-pair · gemini-2.0-flash

    Uncertainty and subjective judgments

    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
     fallu
    -0.81
     sauvages
    -0.78
    oa̍t
    -0.77
     larmes
    -0.77
     étoit
    -0.77
    kháu
    -0.76
     varandra
    -0.75
     vectorielles
    -0.75
     feroit
    -0.75
     définiti
    -0.74
    POSITIVE LOGITS
     comfortable
    0.67
     dubious
    0.64
     questionable
    0.63
     recognizable
    0.61
     controversial
    0.60
     useful
    0.59
     reliable
    0.59
     doubtful
    0.58
     susceptible
    0.58
     meaningful
    0.58
    Activations Density 26.175%

    No Known Activations