© 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. 13234
    Prev
    Next
    INDEX
    Explanations

    the word "linear" and related concepts from math and physics

    oai_token-act-pair · gemini-2.0-flash

    linear

    np_max-act · gemini-2.0-flash
    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
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -1.22
     ſmall
    -1.18
     Reſ
    -1.15
     Monfieur
    -1.13
     preſent
    -1.11
     doubtnut
    -1.09
     Anſ
    -1.09
     itſelf
    -1.07
     ſeveral
    -1.06
     myſelf
    -1.06
    POSITIVE LOGITS
    '
    0.71
     and
    0.67
     '
    0.63
     [
    0.62
    insegna
    0.60
     jegy
    0.60
     S
    0.58
     I
    0.55
     N
    0.55
    ysacchar
    0.54
    Activations Density 1.460%

    No Known Activations