© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11770
    Prev
    Next
    INDEX
    Explanations

    words related to plant life

    oai_token-act-pair · gemini-2.0-flash

    words related to creation or forming

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

    creation

    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
    Vidite
    -0.62
     disambiguazione
    -0.60
    niająca
    -0.60
    lably
    -0.59
    IsContent
    -0.59
    pexpr
    -0.58
     BNF
    -0.57
    
    -0.56
    InitVars
    -0.56
    AndroidJUnit
    -0.56
    POSITIVE LOGITS
     creation
    0.68
     created
    0.67
    Created
    0.65
     forms
    0.63
     creato
    0.63
     Created
    0.62
     Create
    0.61
    Creation
    0.60
     creazione
    0.58
     creación
    0.57
    Activations Density 1.058%

    No Known Activations