© 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. 4841
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and possessive pronouns.

    oai_token-act-pair · gemini-2.0-flash

    concepts of desire and aspiration

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

    dream

    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
     للاسماء
    -0.81
     Rather
    -0.57
    rawtypes
    -0.52
    Rather
    -0.50
     rather
    -0.48
    fragt
    -0.47
    pover
    -0.46
     الحره
    -0.46
    dolu
    -0.45
    geslacht
    -0.45
    POSITIVE LOGITS
     dream
    1.13
     dreaming
    0.90
    dream
    0.88
     wish
    0.81
     dreams
    0.74
     rêver
    0.73
     hope
    0.73
     want
    0.71
    wish
    0.71
     Dream
    0.70
    Activations Density 1.877%

    No Known Activations