© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8837
    Prev
    Next
    INDEX
    Explanations

    words relating to self-reference, mythology, and social ties

    oai_token-act-pair · gemini-2.0-flash

    personal pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     itſelf
    -0.89
     myſelf
    -0.84
     poffible
    -0.77
     prefent
    -0.72
     preſent
    -0.72
     uſed
    -0.71
     Chriftian
    -0.71
     Efq
    -0.71
     neceffary
    -0.68
     fometimes
    -0.68
    POSITIVE LOGITS
    รอบ
    0.53
    ilst
    0.51
    ViewInit
    0.44
     umum
    0.44
    vanja
    0.42
    물
    0.42
     dàng
    0.42
    íté
    0.41
     useCallback
    0.41
    CardModule
    0.41
    Activations Density 4.862%

    No Known Activations