© 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. 13835
    Prev
    Next
    INDEX
    Explanations

    the letter X when used as part of a brand name

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the token 'X'

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

    the letter X

    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
    وزيع
    -0.59
    İstinadlar
    -0.59
    Controllo
    -0.52
     ویکی‌پدیا
    -0.52
    Hozzáférés
    -0.51
    談社
    -0.51
     <=",
    -0.50
     Wikimedijinoj
    -0.49
    पया
    -0.49
     odkazy
    -0.48
    POSITIVE LOGITS
     MainAxisSize
    0.66
     كومونز
    0.62
     riuscito
    0.56
     createSlice
    0.55
     resultCode
    0.53
     disambiguazione
    0.53
    %)$
    0.51
    "}>
    0.50
    '}>
    0.50
     koper
    0.48
    Activations Density 0.313%

    No Known Activations