© 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. 4628
    Prev
    Next
    INDEX
    Explanations

    the words "late" and "early" as well as similar words that are related to time

    oai_token-act-pair · gemini-2.0-flash

    late

    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
    '
    -0.68
    ,
    -0.63
    ing
    -0.63
    (
    -0.58
    <bos>
    -0.57
     for
    -0.55
     used
    -0.54
    \
    -0.54
    ’
    -0.52
    .
    -0.51
    POSITIVE LOGITS
    tvguidetime
    1.20
     ujednoznacz
    1.14
    MigrationBuilder
    1.13
    NUMX
    1.03
    )"),
    1.02
    MessageTagHelper
    1.00
     MainAxisSize
    0.99
    ]]
    0.98
     autorytatywna
    0.98
    :✨
    0.98
    Activations Density 1.930%

    No Known Activations