© 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. 14960
    Prev
    Next
    INDEX
    Explanations

    code used to generate mathematical formulas and their context

    oai_token-act-pair · gemini-2.0-flash

    tokens related to mathematical or logical structures

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

    Foreign 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
     Efq
    -1.02
     Houſe
    -0.84
     ویکی‌پدیا
    -0.81
     purpoſe
    -0.79
     Theſe
    -0.78
     Diſ
    -0.77
     whoſe
    -0.76
    ]--;
    -0.74
    Geplaatst
    -0.74
    UnknownFieldSet
    -0.73
    POSITIVE LOGITS
     kont
    0.60
    onomía
    0.40
     gọn
    0.35
     gele
    0.35
     tem
    0.35
     متعلقه
    0.34
     pion
    0.33
     kamu
    0.33
    Ṛ
    0.32
    SaveChangesAsync
    0.32
    Activations Density 1.818%

    No Known Activations