© 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. 3281
    Prev
    Next
    INDEX
    Explanations

    instances of the word "unknown" and words close to it

    oai_token-act-pair · gemini-2.0-flash

    unknown

    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
    ⓧ
    -0.97
     Monfieur
    -0.87
    ulongan
    -0.86
    出版年
    -0.82
     longtemps
    -0.79
     myſelf
    -0.79
     snippetHide
    -0.79
    UnusedPrivate
    -0.78
     Efq
    -0.77
     ifrån
    -0.77
    POSITIVE LOGITS
    __':
    0.60
    وه
    0.60
     [*]
    0.59
    __":
    0.58
     mem
    0.57
                     
    0.57
    mem
    0.55
     Sir
    0.55
                                  
    0.55
                           
    0.55
    Activations Density 1.660%

    No Known Activations