© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4949
    Prev
    Next
    INDEX
    Explanations

    Andreas Mies / arXiv (preprint)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     shutt
    0.84
     shuttle
    0.82
     Badminton
    0.75
     Shuttle
    0.74
     badminton
    0.73
     बैड
    0.62
    🏸
    0.59
     Uber
    0.50
     BAD
    0.47
     Indonesia
    0.47
    POSITIVE LOGITS
     टेनिस
    0.39
    ATP
    0.38
     Cev
    0.38
     sac
    0.37
    砖
    0.37
     지
    0.37
     Hernández
    0.36
     Gener
    0.35
     WILD
    0.35
    Nurse
    0.35
    Activations Density 0.011%

    No Known Activations