© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3877
    Prev
    Next
    INDEX
    Explanations

    phrases with certain prepositions like "of" and "from" followed by words indicating impact like "results", "product" or "lead".

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    stahl
    -0.50
    문
    -0.50
    andExpect
    -0.47
     corri
    -0.46
    číta
    -0.45
     वाली
    -0.44
    Geografi
    -0.44
    Vea
    -0.44
     verso
    -0.43
    BeginContext
    -0.42
    POSITIVE LOGITS
    AndEndTag
    0.88
    sizeCache
    0.84
    <bos>
    0.79
     AssemblyTitle
    0.76
     Extragalactic
    0.73
     frutto
    0.71
    ibouti
    0.70
     fruto
    0.70
     frutos
    0.69
    featureID
    0.67
    Activations Density 1.308%

    No Known Activations