© 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. 11214
    Prev
    Next
    INDEX
    Explanations

    instances of variable-length words ending in the letter "a"

    oai_token-act-pair · gemini-2.0-flash

    a

    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
    a
    -2.73
    e
    -0.99
    A
    -0.97
    aing
    -0.78
    aA
    -0.75
    ا
    -0.74
    o
    -0.73
    aas
    -0.71
    aie
    -0.71
    ahi
    -0.70
    POSITIVE LOGITS
     resourceCulture
    0.80
    ⤹
    0.71
    IsContent
    0.66
     виправивши
    0.64
    +#+
    0.63
     ویکی‌پدیا
    0.63
    tioners
    0.63
    monials
    0.63
    Cordialement
    0.62
    ysacchar
    0.61
    Activations Density 1.285%

    No Known Activations