© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13598
    Prev
    Next
    INDEX
    Explanations

    contractions and possessives

    oai_token-act-pair · gemini-2.0-flash

    apostrophe character

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     char
    -0.62
     br
    -0.59
     cara
    -0.55
    mergeFrom
    -0.53
    出版年
    -0.51
    twimg
    -0.51
    TabIndex
    -0.51
     Br
    -0.51
     gra
    -0.50
    面
    -0.50
    POSITIVE LOGITS
     Majefty
    0.80
     pleaſure
    0.69
     Theſe
    0.68
     Reſ
    0.64
     تانيه
    0.63
     occaf
    0.63
     vectorielles
    0.63
     photolibrary
    0.60
     neceff
    0.60
     Diſ
    0.60
    Activations Density 1.222%

    No Known Activations