© 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. 4515
    Prev
    Next
    INDEX
    Explanations

    words and phrases found in descriptions of science fiction plots, especially space opera

    oai_token-act-pair · gemini-2.0-flash

    space battleships

    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
     $
    -0.49
     $\$
    -0.48
    नलिखित
    -0.47
    curacies
    -0.47
     mélang
    -0.46
     lèvres
    -0.45
     pagare
    -0.42
    cyj
    -0.42
     Americana
    -0.42
     $?
    -0.41
    POSITIVE LOGITS
     AttributeSet
    0.67
    execSQL
    0.66
     ioutil
    0.63
    WireFormatLite
    0.60
    makeConstraints
    0.59
    urlopen
    0.58
     setOpen
    0.57
    dération
    0.56
    ISupport
    0.56
    IBarButtonItem
    0.56
    Activations Density 13.133%

    No Known Activations