© 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. 93433
    Prev
    Next
    INDEX
    Explanations

    acronyms or mnemonics

    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_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
    ité
    0.54
     стать
    0.51
     поста
    0.50
     comedians
    0.49
    ansom
    0.49
     wher
    0.49
     &
    0.48
     scaffolds
    0.48
     soooo
    0.48
     статей
    0.48
    POSITIVE LOGITS
    ção
    0.48
     próprio
    0.46
     prossimo
    0.46
    k
    0.44
    風
    0.44
    １
    0.44
    ঞ্চলিক
    0.43
    一つ
    0.43
    1
    0.43
    명을
    0.43
    Activations Density 0.004%

    No Known Activations