© 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. 15652
    Prev
    Next
    INDEX
    Explanations

    different forms of the word "feel"

    oai_token-act-pair · gemini-2.0-flash

    feel

    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
    RegressionTest
    -0.87
    AnchorStyles
    -0.73
    DockStyle
    -0.68
    migrationBuilder
    -0.64
     Italijanski
    -0.62
    \{\\
    -0.59
    StoryboardSegue
    -0.59
     BoxFit
    -0.57
    Koordinaten
    -0.56
    IUrlHelper
    -0.56
    POSITIVE LOGITS
    queous
    0.50
     Unsc
    0.48
    jewództ
    0.47
    croix
    0.47
     used
    0.46
    eterangan
    0.46
    ICLE
    0.45
    sidemargin
    0.45
     colonized
    0.44
    jectives
    0.44
    Activations Density 0.324%

    No Known Activations