© 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. 1800
    Prev
    Next
    INDEX
    Explanations

    phrases related to maintaining something or keeping watch.

    oai_token-act-pair · 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
     Rufus
    -0.45
    jší
    -0.45
    osoba
    -0.44
    oward
    -0.44
     TPP
    -0.43
    assumed
    -0.43
    reibe
    -0.42
    dd
    -0.42
     propos
    -0.42
    مصادر
    -0.41
    POSITIVE LOGITS
    InjectAttribute
    0.68
     protoimpl
    0.66
    :^(
    0.65
     StatelessWidget
    0.65
     NSCoder
    0.63
    EndGlobalSection
    0.61
     dAtA
    0.61
     unknownFields
    0.61
     оригіналу
    0.60
     Signalez
    0.59
    Activations Density 7.839%

    No Known Activations