© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2912
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Do" (and "До" in a different alphabet)

    oai_token-act-pair · gemini-2.0-flash

    the word "до" and similar variations

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

    Words meaning "until"

    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
     فريبيس
    -0.73
     estimés
    -0.71
    BeginContext
    -0.68
     estekak
    -0.61
     kaynağından
    -0.59
     consultato
    -0.57
    ANNES
    -0.56
    ритори
    -0.56
     ContentValues
    -0.54
     useState
    -0.53
    POSITIVE LOGITS
     credere
    0.59
    :✨
    0.56
    óngase
    0.52
     Référence
    0.51
     condividere
    0.50
     purpoſe
    0.50
     küpe
    0.49
     bileklik
    0.48
     uscire
    0.47
    äler
    0.47
    Activations Density 0.423%

    No Known Activations