© 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. 13678
    Prev
    Next
    INDEX
    Explanations

    the prefix "un"

    oai_token-act-pair · gemini-2.0-flash

    un

    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
    lakukan
    -0.55
    pédie
    -0.54
    odus
    -0.54
     Schult
    -0.54
     تانيه
    -0.54
    chaise
    -0.53
    anderson
    -0.52
    bosity
    -0.52
    OGND
    -0.52
     Normdatei
    -0.51
    POSITIVE LOGITS
    FormTagHelper
    0.83
    expandindo
    0.64
    migrationBuilder
    0.49
     Paglinawan
    0.49
     flattered
    0.48
     gainera
    0.48
     grail
    0.47
    piram
    0.47
    Diweddarwch
    0.47
     himo
    0.46
    Activations Density 0.219%

    No Known Activations