© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13257
    Prev
    Next
    INDEX
    Explanations

    the word "flexible"

    oai_token-act-pair · gemini-2.0-flash

    flexible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     flexible
    -2.06
     flexibility
    -2.02
     Flexible
    -1.92
    Flexible
    -1.89
    flexible
    -1.84
     Flexibility
    -1.74
    Flexibility
    -1.66
     flexibles
    -1.63
     flexib
    -1.51
     flexibel
    -1.44
    POSITIVE LOGITS
    帖最后由
    0.57
    plained
    0.50
    ronym
    0.49
     tagName
    0.48
    tonsoft
    0.48
    interopRequire
    0.48
    MLLoader
    0.47
     sauer
    0.46
     FormBuilder
    0.46
    Wię
    0.46
    Activations Density 1.369%

    No Known Activations