© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3097
    Prev
    Next
    INDEX
    Explanations

    the words or concepts "forward" and "backward" and the related idea of looking back

    oai_token-act-pair · gemini-2.0-flash

    backward

    np_max-act · gemini-2.0-flash

    backward

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     igång
    -0.60
     klara
    -0.59
     Alfaro
    -0.59
     esterna
    -0.57
    ISODE
    -0.56
    chtenstein
    -0.56
    <bos>
    -0.55
    SocketChannel
    -0.55
     tecnici
    -0.55
     étanche
    -0.55
    POSITIVE LOGITS
    adaptiveStyles
    0.65
     <>",
    0.63
    $_['
    0.61
     Initialise
    0.60
     localisation
    0.60
     Deak
    0.60
     Leona
    0.60
    BeginInit
    0.60
     initialise
    0.57
     Efq
    0.56
    Activations Density 0.729%

    No Known Activations