© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3424
    Prev
    Next
    INDEX
    Explanations

    the digit '2' in different contexts, especially dates

    oai_token-act-pair · gemini-2.0-flash

    Citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Former
    -0.32
    <h1>
    -0.30
    The
    -0.26
     jellemző
    -0.26
    tanleria
    -0.26
     tartalomajánló
    -0.26
    junit
    -0.24
    getFloat
    -0.24
    سطس
    -0.23
    Death
    -0.23
    POSITIVE LOGITS
    <bos>
    0.60
    WithIOException
    0.60
     CreateTagHelper
    0.59
    ]")]
    0.59
    出版年
    0.57
    AnimationsModule
    0.53
    UserScript
    0.50
    enumi
    0.50
    tvguidetime
    0.49
    awtextra
    0.48
    Activations Density 0.028%

    No Known Activations