© 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. 4063
    Prev
    Next
    INDEX
    Explanations

    terminology and concepts related to biochemistry and molecular biology, with a focus on proteins, viruses, and related processes.

    oai_token-act-pair · gemini-2.0-flash

    words or phrases containing "the"

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

    of

    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
    adaptiveStyles
    -0.77
     صوتيه
    -0.71
     disambiguazione
    -0.71
     stället
    -0.70
     noires
    -0.68
     fédé
    -0.66
     disparu
    -0.64
     feroit
    -0.63
     rumahnya
    -0.62
     noastră
    -0.61
    POSITIVE LOGITS
     the
    0.69
    othesis
    0.60
    unteer
    0.57
    icap
    0.54
     these
    0.54
    phemy
    0.52
    Bigr
    0.52
     mon
    0.51
    idon
    0.51
    evich
    0.49
    Activations Density 9.694%

    No Known Activations