© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13375
    Prev
    Next
    INDEX
    Explanations

    common short words near words describing opinions and media

    oai_token-act-pair · gemini-2.0-flash

    terms related to sampling and presentation

    np_token-act-pair-logits · gpt-4o-mini

    a/an

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     purpoſe
    -0.68
     poffible
    -0.65
     ſeveral
    -0.61
     becauſe
    -0.60
     Jefus
    -0.58
     faptul
    -0.58
     whoſe
    -0.57
     fhew
    -0.57
     InputDecoration
    -0.56
     leſs
    -0.56
    POSITIVE LOGITS
     look
    0.58
    MLLoader
    0.56
     taste
    0.56
     behind
    0.54
     Behind
    0.54
    出版年
    0.54
    ArgsConstructor
    0.53
    Diweddarwch
    0.53
    WriteAttribute
    0.52
     LOOK
    0.52
    Activations Density 1.011%

    No Known Activations