© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6310
    Prev
    Next
    INDEX
    Explanations

    words that function as proper nouns or are related to academic research

    oai_token-act-pair · gemini-2.0-flash

    scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Permeability
    -1.85
     Dividends
    -1.81
     Tumors
    -1.80
     Garnish
    -1.76
     Abdomen
    -1.75
     Salinity
    -1.74
     Ideology
    -1.71
     Gown
    -1.71
     Viability
    -1.71
     Parity
    -1.70
    POSITIVE LOGITS
     In
    1.30
     The
    1.30
     A
    1.29
     Co
    1.16
     C
    1.16
     And
    1.16
     F
    1.14
     S
    1.14
     We
    1.14
     An
    1.13
    Activations Density 6.814%

    No Known Activations