© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15699
    Prev
    Next
    INDEX
    Explanations

    words related to a pleasant experience or recent events

    oai_token-act-pair · gemini-2.0-flash

    day

    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
    Negative Logits
    lgari
    -0.66
     насељу
    -0.54
    .*")]
    -0.53
    出版年
    -0.52
    ularity
    -0.49
    Tikang
    -0.49
    amu
    -0.47
     صوتيه
    -0.46
    روابط
    -0.46
    alas
    -0.45
    POSITIVE LOGITS
    kuuta
    0.65
    tvguidetime
    0.61
     initComponents
    0.61
     Murch
    0.55
    andExpect
    0.54
    BeginInit
    0.53
     Malaya
    0.52
    posób
    0.52
    SequentialGroup
    0.52
    ágok
    0.48
    Activations Density 0.361%

    No Known Activations