© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11069
    Prev
    Next
    INDEX
    Explanations

    mentions of brushes and the act of using them to apply something to eyebrows.

    oai_token-act-pair · gemini-2.0-flash

    cleaning/brushing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    featureID
    -0.81
     Normdatei
    -0.73
     tartalomajánló
    -0.69
     estimés
    -0.69
    Datuak
    -0.69
     refusé
    -0.67
     CURIAM
    -0.62
     azioni
    -0.60
    oules
    -0.60
    躇
    -0.58
    POSITIVE LOGITS
    nonatomic
    0.49
     ligiloj
    0.48
    ftrag
    0.47
    ▾
    0.46
    ArgumentParser
    0.46
    :]:
    0.46
     Roskov
    0.45
    SpringBoot
    0.44
    moto
    0.42
    damit
    0.41
    Activations Density 1.034%

    No Known Activations