© 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. 14093
    Prev
    Next
    INDEX
    Explanations

    uses of "that" and "who", possibly as conjunctions

    oai_token-act-pair · gemini-2.0-flash

    relative pronouns

    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
     Indeed
    -0.59
    indeed
    -0.59
    jaer
    -0.57
    ReusableCell
    -0.56
    Indeed
    -0.53
     efectivamente
    -0.53
    corrhi
    -0.52
     Verſ
    -0.52
     indeed
    -0.50
    agaimana
    -0.49
    POSITIVE LOGITS
     poveznice
    0.67
    expandindo
    0.66
    routeProvider
    0.66
     препратки
    0.66
     tartalomajánló
    0.66
    rungsseite
    0.63
    principalTable
    0.62
    Билгалдахарш
    0.57
    #
    0.56
    umoj
    0.56
    Activations Density 3.358%

    No Known Activations