© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2032
    Prev
    Next
    INDEX
    Explanations

    language that includes us, our, that, with numbers and quantifiers.

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     our
    -1.60
    Our
    -1.40
     Our
    -1.37
    our
    -1.37
     ourselves
    -1.35
     ours
    -1.32
     we
    -1.26
    我们的
    -1.21
     OUR
    -1.21
    we
    -1.18
    POSITIVE LOGITS
     henvisninger
    0.74
     defaultstate
    0.69
    GTCX
    0.65
     ujednoznacz
    0.64
     kaynağından
    0.63
     autorytatywna
    0.60
    homonymie
    0.59
    Espèce
    0.59
    ArgsConstructor
    0.59
     lenker
    0.59
    Activations Density 2.331%

    No Known Activations