© 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. 725
    Prev
    Next
    INDEX
    Explanations

    words that have multiple meanings or are used in different fields, and can involve measurements or research.

    oai_token-act-pair · gemini-2.0-flash

    scientific studies

    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
     was
    -1.85
    was
    -1.61
    Was
    -1.59
     Was
    -1.48
     был
    -1.21
     была
    -1.21
     were
    -1.13
     WAS
    -1.07
     був
    -1.05
     wasn
    -1.05
    POSITIVE LOGITS
    StoryboardSegue
    0.78
    ⓧ
    0.65
    >>()
    0.60
     woken
    0.59
     caught
    0.59
     seized
    0.58
     spilled
    0.56
     penetrated
    0.56
     burned
    0.56
     NgModule
    0.56
    Activations Density 13.117%

    No Known Activations