© 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-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57523
    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_11_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
     atra
    0.46
     utilise
    0.44
     I
    0.44
    面對
    0.44
     지하
    0.44
     determinate
    0.43
    ulph
    0.43
     (\
    0.42
     đông
    0.42
     utilising
    0.42
    POSITIVE LOGITS
     پہ
    0.51
    boys
    0.49
    被告
    0.48
    ężczy
    0.48
    eret
    0.47
    neurons
    0.46
    markers
    0.45
    ानंद
    0.45
    բ
    0.45
    anigans
    0.45
    Activations Density 0.000%

    No Known Activations