© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21672
    Prev
    Next
    INDEX
    Explanations

    charities or aid

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     umur
    0.43
    楫
    0.40
     ಪುಟ
    0.38
     dvar
    0.36
     baar
    0.35
    vering
    0.34
     depender
    0.34
    鍝
    0.34
     depend
    0.34
     ছো
    0.34
    POSITIVE LOGITS
     Save
    1.77
    Save
    1.64
     save
    1.53
    save
    1.34
     SAVE
    1.25
    SAVE
    1.20
     saves
    1.10
     Doctors
    1.08
     UNF
    1.06
    UN
    1.05
    Activations Density 0.029%

    No Known Activations