© 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. 3729
    Prev
    Next
    INDEX
    Explanations

    the words and context surrounding "From," "To," and "via," possibly related to email headers and circuit board design

    oai_token-act-pair · gemini-2.0-flash

    from/via

    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
    <bos>
    -2.45
     transférez
    -0.86
    uxxxx
    -0.84
    Geplaatst
    -0.83
    InitVars
    -0.81
    ########.
    -0.79
    دانشنامهٔ
    -0.79
     saites
    -0.77
    yntaxException
    -0.73
    enumii
    -0.72
    POSITIVE LOGITS
     gewor
    0.41
     flèche
    0.41
    乏
    0.40
     Comer
    0.40
    мед
    0.38
     renseignements
    0.38
    例
    0.36
    guera
    0.36
     aang
    0.36
    dom
    0.36
    Activations Density 2.655%

    No Known Activations