© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33421
    Prev
    Next
    INDEX
    Explanations

    Spanish, French, and English continuations

    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_31_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
    ඵ
    0.37
     unripe
    0.37
    显得
    0.36
    गिंग
    0.36
    йся
    0.36
     pouring
    0.35
    pher
    0.35
     asphalt
    0.35
     heresy
    0.35
    няется
    0.35
    POSITIVE LOGITS
    担保
    0.41
     Progressives
    0.38
    <end_of_turn>
    0.37
     發
    0.37
    Delhi
    0.37
    殮
    0.37
     Groups
    0.36
    代谢
    0.36
     发
    0.35
    發
    0.35
    Activations Density 0.008%

    No Known Activations