© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6563
    Prev
    Next
    INDEX
    Explanations

    prepositions and possessive pronouns followed by nouns or proper nouns.

    oai_token-act-pair · gemini-2.0-flash

    rescue-related words

    np_token-act-pair-logits · gpt-4o-mini

    help/assistance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    OMES
    -0.47
    stree
    -0.47
    stwie
    -0.44
    UnifiedTopology
    -0.43
    ± 
    -0.43
    leyebilirsiniz
    -0.43
     illustre
    -0.43
    ebus
    -0.43
     mantenerse
    -0.42
    гипет
    -0.42
    POSITIVE LOGITS
     rescue
    0.94
     aid
    0.87
     assistance
    0.75
     disposal
    0.75
     help
    0.74
    rescue
    0.66
     Rescue
    0.65
     hjälp
    0.65
     benefit
    0.63
     @"/
    0.62
    Activations Density 0.938%

    No Known Activations