© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13411
    Prev
    Next
    INDEX
    Explanations

    words used when reviewing products, locations, or lifestyles

    oai_token-act-pair · gemini-2.0-flash

    luxury or premium

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     nærm
    -0.54
    ContextHolder
    -0.52
     pauvres
    -0.51
    UnusedPrivate
    -0.49
     dår
    -0.48
     picioare
    -0.46
     cérami
    -0.46
     phénom
    -0.45
     vérit
    -0.45
     muun
    -0.45
    POSITIVE LOGITS
    MemoryWarning
    0.71
    SequentialGroup
    0.65
    хьтан
    0.65
    MLLoader
    0.60
     createSprite
    0.54
    postsleuth
    0.54
     Kirkwood
    0.52
    twimg
    0.52
    PostInfinity
    0.52
     lifestyles
    0.52
    Activations Density 3.680%

    No Known Activations