© 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. 9466
    Prev
    Next
    INDEX
    Explanations

    the word "Dark" and words with strong negative connotations.

    oai_token-act-pair · gemini-2.0-flash

    dark

    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
     dark
    -3.17
     Dark
    -2.92
    Dark
    -2.86
    dark
    -2.86
     DARK
    -2.67
    DARK
    -2.45
     darker
    -2.31
     darkest
    -1.91
     darkened
    -1.86
     darken
    -1.84
    POSITIVE LOGITS
    Javadoc
    0.58
    /**
    0.57
    GenerationType
    0.46
    XMLSchema
    0.44
    IOException
    0.42
    hynch
    0.42
    falt
    0.41
    asymp
    0.41
     Eind
    0.41
    etra
    0.40
    Activations Density 3.046%

    No Known Activations