© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6882
    Prev
    Next
    INDEX
    Explanations

    Elliott + ity/IT

    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
    *}{
    0.38
     curviliné
    0.34
     '+':
    0.33
    ారి
    0.33
     sorprendente
    0.33
    +:
    0.33
    ]]:
    0.32
     `>`,
    0.32
    ecc
    0.32
     duck
    0.32
    POSITIVE LOGITS
    کٹ
    0.39
     परामर्श
    0.37
    ัญ
    0.36
    زمة
    0.35
     раза
    0.35
    ኑ
    0.35
    Lake
    0.34
     inclusive
    0.33
     tratta
    0.33
     सहा
    0.32
    Activations Density 0.014%

    No Known Activations