© 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. 11055
    Prev
    Next
    INDEX
    Explanations

    the word "factors" and words associated with math

    oai_token-act-pair · gemini-2.0-flash

    factors

    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
    rawDesc
    -0.59
    ReusableCell
    -0.59
     But
    -0.57
     "
    -0.57
     .
    -0.54
     "..\..\
    -0.54
     '
    -0.53
     O
    -0.52
     Big
    -0.52
     v
    -0.50
    POSITIVE LOGITS
    <bos>
    1.47
     itſelf
    1.09
     myſelf
    0.99
     cauſe
    0.97
     houſe
    0.92
     raiſ
    0.90
     himſelf
    0.89
     deſt
    0.88
     Theſe
    0.88
     purpoſe
    0.87
    Activations Density 0.994%

    No Known Activations