© 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. 12515
    Prev
    Next
    INDEX
    Explanations

    the word "outstanding"

    oai_token-act-pair · gemini-2.0-flash

    outstanding

    np_max-act · gemini-2.0-flash

    outstanding

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     Eſ
    -1.56
     Efq
    -1.51
     houſe
    -1.43
     purpoſe
    -1.43
     Theſe
    -1.37
     myſelf
    -1.36
     Reſ
    -1.36
     Houſe
    -1.34
     Jefus
    -1.33
     raiſ
    -1.30
    POSITIVE LOGITS
    ,
    0.74
    /
    0.63
    </i>
    0.61
    .
    0.61
    <b>
    0.60
     /
    0.60
     ‘
    0.59
    <i>
    0.59
    al
    0.58
    <u>
    0.57
    Activations Density 1.299%

    No Known Activations