© 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. 13093
    Prev
    Next
    INDEX
    Explanations

    words associated with sports, violence, and underestimation

    oai_token-act-pair · gemini-2.0-flash

    Random statements

    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
     some
    -0.52
     gj
    -0.48
    some
    -0.47
     algum
    -0.47
    Attempts
    -0.46
     DESCR
    -0.46
    évaluateur
    -0.46
    attempts
    -0.45
     Attempts
    -0.45
     sık
    -0.44
    POSITIVE LOGITS
     '\\;'
    0.86
    __':
    0.74
    новништво
    0.68
    MemoryWarning
    0.65
     intimidating
    0.62
     menacing
    0.60
    ็จ
    0.59
    nextDouble
    0.59
    uxxxx
    0.59
    InjectAttribute
    0.59
    Activations Density 1.676%

    No Known Activations