© 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. 13875
    Prev
    Next
    INDEX
    Explanations

    Vietnamese text, including names, locations, and possibly numerical data associated with tours or schedules.

    oai_token-act-pair · gemini-2.0-flash

    Vietnamese names or locations

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

    Vietnamese words

    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
     purpoſe
    -0.85
     Reſ
    -0.85
     Majefty
    -0.84
     Monfieur
    -0.83
     Efq
    -0.82
     pleaſure
    -0.82
     ſtate
    -0.81
     Diſ
    -0.80
     houſe
    -0.77
     reaſon
    -0.75
    POSITIVE LOGITS
     nh
    0.60
     và
    0.56
     Thi
    0.56
     trong
    0.55
     Chim
    0.54
     occupé
    0.54
     thu
    0.53
     Phi
    0.52
     Th
    0.52
     Nh
    0.52
    Activations Density 1.794%

    No Known Activations