© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14885
    Prev
    Next
    INDEX
    Explanations

    abbreviated author names and journal references

    oai_token-act-pair · gemini-2.0-flash

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ,
    -0.50
     or
    -0.48
     and
    -0.47
    .
    -0.47
     –
    -0.44
    :
    -0.42
    ;
    -0.41
    ...
    -0.40
    iteritems
    -0.40
     larger
    -0.39
    POSITIVE LOGITS
    fjspx
    0.96
     ویکی‌پدیا
    0.93
    GEBURTSDATUM
    0.89
     &___
    0.79
    DoubleQuotes
    0.79
     autorytatywna
    0.79
     ostavi
    0.77
     الحره
    0.75
    parsedMessage
    0.75
    enumii
    0.75
    Activations Density 8.220%

    No Known Activations