© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12472
    Prev
    Next
    INDEX
    Explanations

    various personal pronouns or verb endings in languages other than English

    oai_token-act-pair · gemini-2.0-flash

    Foreign language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    WriteBarrier
    -0.61
    ANDUM
    -0.60
     calendriers
    -0.57
     allons
    -0.57
    Selección
    -0.57
    pillars
    -0.57
    WSGI
    -0.57
     AssemblyCulture
    -0.56
    assertNotNull
    -0.55
    cephala
    -0.55
    POSITIVE LOGITS
     would
    1.22
    would
    1.11
    Would
    1.09
     Would
    1.08
     WOULD
    0.95
     olisi
    0.81
     wouldn
    0.77
     lenne
    0.77
     skulle
    0.76
     Wouldn
    0.76
    Activations Density 0.669%

    No Known Activations