© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12865
    Prev
    Next
    INDEX
    Explanations

    words with multiple meanings pertaining to sustenance and societal conventions.

    oai_token-act-pair · gemini-2.0-flash

    Food

    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
    SourceChecksum
    -1.01
    Материалы
    -0.94
     فريبيس
    -0.92
     InputDecoration
    -0.84
    Materiales
    -0.82
     Materials
    -0.79
    Materials
    -0.79
     Material
    -0.75
    المشاركات
    -0.73
    tagext
    -0.72
    POSITIVE LOGITS
     spreads
    0.48
     condi
    0.48
     balanced
    0.47
     healthiest
    0.45
     healthier
    0.44
     grocery
    0.43
     healthy
    0.43
     treat
    0.43
     preparation
    0.42
    FormTagHelper
    0.42
    Activations Density 2.183%

    No Known Activations