© 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. 33608
    Prev
    Next
    INDEX
    Explanations

    company address placeholder

    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
     끊
    0.43
    끊
    0.40
     NO
    0.36
     noting
    0.36
    detect
    0.36
    dioxide
    0.36
     Infer
    0.35
    分别为
    0.35
     conversation
    0.35
     Victims
    0.35
    POSITIVE LOGITS
    *((*
    0.40
     Mogo
    0.39
    鑣
    0.39
    లీ
    0.38
    綰
    0.36
    Bounded
    0.35
     lass
    0.35
    笵
    0.35
    லே
    0.34
     considere
    0.34
    Activations Density 0.001%

    No Known Activations