© 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. 13296
    Prev
    Next
    INDEX
    Explanations

    words indicating quantities or an amount - especially the word "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
     a
    -0.59
    semantics
    -0.40
     мо
    -0.39
    ]")]
    -0.39
     for
    -0.39
    з
    -0.38
    cox
    -0.38
    .
    -0.38
    kun
    -0.37
     einen
    -0.37
    POSITIVE LOGITS
    CloseOperation
    0.93
     препратки
    0.73
    PreferredItem
    0.73
    InjectAttribute
    0.72
    AutoScale
    0.68
     intStringLen
    0.67
    DeleteBehavior
    0.67
    IBOutlet
    0.66
    Portail
    0.66
    eae
    0.66
    Activations Density 0.549%

    No Known Activations