© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4644
    Prev
    Next
    INDEX
    Explanations

    the word "input" and words that often appear near it like "output" and "tty"

    oai_token-act-pair · gemini-2.0-flash

    input

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    n
    -0.88
    d
    -0.87
    c
    -0.86
    m
    -0.85
    r
    -0.83
    <bos>
    -0.79
    t
    -0.79
    l
    -0.73
    p
    -0.73
    b
    -0.72
    POSITIVE LOGITS
     MainAxisSize
    1.14
     pinulongan
    1.11
     تضيفلها
    1.10
     ویکی‌پدیا
    1.10
    yntaxException
    1.09
     GenerationType
    1.01
     ویکی‌پدیای
    0.99
    principalTable
    0.98
    aarrggbb
    0.98
    OGND
    0.97
    Activations Density 1.650%

    No Known Activations