© 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. 12164
    Prev
    Next
    INDEX
    Explanations

    the word "dry."

    oai_token-act-pair · gemini-2.0-flash

    dry

    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
     stessi
    -0.58
     mesmos
    -0.52
     précie
    -0.51
     mesmas
    -0.50
    AccessorTable
    -0.50
     beginnetje
    -0.49
     boucles
    -0.49
    kmale
    -0.49
     vermelhas
    -0.48
    ējās
    -0.47
    POSITIVE LOGITS
     Roskov
    0.64
    PerformLayout
    0.63
    ChromeDriver
    0.60
    astify
    0.58
    ifico
    0.56
    pasta
    0.56
    MethodManager
    0.55
     pasta
    0.54
    UNO
    0.54
    AnchorStyles
    0.54
    Activations Density 1.115%

    No Known Activations