© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10034
    Prev
    Next
    INDEX
    Explanations

    places where a paper refers to more than one author using "et al"

    oai_token-act-pair · gemini-2.0-flash

    et

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -0.61
     (
    -0.49
    :
    -0.45
    <eos>
    -0.44
    ↵↵
    -0.44
     
    -0.44
     her
    -0.43
    ...
    -0.43
     zu
    -0.42
    icie
    -0.42
    POSITIVE LOGITS
     Monfieur
    0.95
     myſelf
    0.93
     Efq
    0.91
     Reſ
    0.90
     Theſe
    0.89
     iſt
    0.88
     ſeveral
    0.86
    Билгалдахарш
    0.85
    ^(@)
    0.85
     Eſ
    0.84
    Activations Density 0.086%

    No Known Activations