© 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. 5289
    Prev
    Next
    INDEX
    Explanations

    contractions using "'m" and "'re" and the words "are."

    oai_token-act-pair · gemini-2.0-flash

    future tense

    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
     is
    -1.38
     are
    -1.02
     está
    -0.90
     están
    -0.82
    are
    -0.75
     Estoy
    -0.69
     am
    -0.68
     Are
    -0.67
     estoy
    -0.67
    is
    -0.66
    POSITIVE LOGITS
     resourceCulture
    0.93
     EconPapers
    0.91
     الحره
    0.76
    KommentareTeilen
    0.75
     typelib
    0.67
    StructEnd
    0.65
     дописавши
    0.64
     Normdatei
    0.64
     समीक्षक
    0.63
    RUnlock
    0.63
    Activations Density 0.534%

    No Known Activations