© 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. 7972
    Prev
    Next
    INDEX
    Explanations

    mentions of gene and protein markers, like HOX and AMP.

    oai_token-act-pair · gemini-2.0-flash

    scientific, medical texts

    np_max-act-logits · gemini-2.0-flash

    say "all-caps abbreviations"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    ros
    -0.55
    si
    -0.55
    os
    -0.54
    za
    -0.54
    ma
    -0.53
    z
    -0.53
    che
    -0.53
    ut
    -0.53
    ik
    -0.53
    ot
    -0.52
    POSITIVE LOGITS
    drawal
    0.62
    successfully
    0.54
    ficulty
    0.53
    expectations
    0.52
     CreateTagHelper
    0.52
    bibfield
    0.52
    steering
    0.52
    sounding
    0.51
    satisfied
    0.51
    encouragement
    0.51
    Activations Density 4.755%

    No Known Activations