© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11484
    Prev
    Next
    INDEX
    Explanations

    biological terms with suffixes "-ine", "-cyte", "-ular"

    oai_token-act-pair · gemini-2.0-flash

    say "the ending -ulate/ular/ulation/ules/uli/ulants/ulatory"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     skid
    -0.41
    mainAxisSize
    -0.39
    neiden
    -0.38
    牢
    -0.36
    __).
    -0.36
    jší
    -0.35
    着
    -0.35
     Верхов
    -0.34
     Rais
    -0.34
    AFTA
    -0.34
    POSITIVE LOGITS
    ul
    1.23
    UL
    1.15
    ulat
    1.12
    ulata
    1.08
    ulas
    1.02
    uler
    1.01
    ulen
    1.00
    ulator
    1.00
    ulan
    0.99
    ulation
    0.98
    Activations Density 1.325%

    No Known Activations