© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132799
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    this
    1.27
    iest
    1.20
    on
    1.17
    for
    1.15
    us
    1.12
    nolds
    1.11
    buyers
    1.11
    7
    1.05
    pets
    1.05
    kry
    1.05
    POSITIVE LOGITS
     I
    1.06
    1.05
     TO
    0.90
     choir
    0.88
     song
    0.84
     newspaper
    0.84
     But
    0.80
     gustaría
    0.80
     หรือ
    0.79
    <0xAB>
    0.79
    Activations Density 0.000%

    No Known Activations