© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14253
    Prev
    Next
    INDEX
    Explanations

    instances of legal or scientific writing

    oai_token-act-pair · gemini-2.0-flash

    might, may

    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
    expandindo
    -0.59
    POSSIBLE
    -0.52
     probable
    -0.51
     Possible
    -0.51
     POSSIBLE
    -0.50
     possible
    -0.50
    possible
    -0.48
    ेशा
    -0.47
     shouldBe
    -0.47
    möglich
    -0.47
    POSITIVE LOGITS
     might
    1.34
     may
    1.16
     Might
    1.11
    May
    1.05
     May
    1.05
    Might
    1.05
    might
    1.02
    may
    0.96
     MIGHT
    0.87
     mig
    0.85
    Activations Density 1.149%

    No Known Activations