© 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. 13491
    Prev
    Next
    INDEX
    Explanations

    words related to getting or having smooth skin

    oai_token-act-pair · 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
    
    -0.70
    principalTable
    -0.64
    ſelf
    -0.62
    postolic
    -0.62
     مرئيه
    -0.61
    nachron
    -0.61
    oa̍t
    -0.60
    ########.
    -0.59
    ➋
    -0.58
    PreInfinity
    -0.58
    POSITIVE LOGITS
    ubourg
    0.52
     firm
    0.50
    QMetaType
    0.49
     sm
    0.49
     Sm
    0.48
    addPreferredGap
    0.48
    lė
    0.48
     NgModule
    0.48
     luminance
    0.45
     lit
    0.44
    Activations Density 0.642%

    No Known Activations