© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11558
    Prev
    Next
    INDEX
    Explanations

    words and phrases about unity and action

    oai_token-act-pair · gemini-2.0-flash

    variations of "we"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     they
    -2.20
    Their
    -2.14
    They
    -2.11
     They
    -2.09
    they
    -2.05
     their
    -2.05
    their
    -2.05
    Mereka
    -2.03
     Mereka
    -2.03
     Their
    -2.02
    POSITIVE LOGITS
     we
    0.76
     our
    0.63
     kita
    0.53
     We
    0.46
    نا
    0.45
     nossas
    0.45
    our
    0.44
    我们
    0.43
     нами
    0.42
     nossa
    0.42
    Activations Density 0.515%

    No Known Activations