© 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. 12851
    Prev
    Next
    INDEX
    Explanations

    phrases asking or discussing if there is utility or purpose

    oai_token-act-pair · gemini-2.0-flash

    disagreements/arguments

    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
    +#+#
    -0.73
    errHandler
    -0.64
    writeFieldEnd
    -0.57
     يتيمه
    -0.56
     AssemblyCulture
    -0.54
     sos
    -0.53
    Tikang
    -0.51
     verra
    -0.51
     Mauritania
    -0.50
    InputBorder
    -0.50
    POSITIVE LOGITS
    ValueGeneration
    0.53
    Externé
    0.52
     geslacht
    0.52
     ineffectual
    0.52
     számára
    0.50
     useless
    0.49
     propósito
    0.49
     propósitos
    0.49
     souhaitent
    0.49
     miatt
    0.48
    Activations Density 1.509%

    No Known Activations