© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16859
    Prev
    Next
    INDEX
    Explanations

    Reuters, Re:Zero, Rexburg

    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
     tastefully
    0.39
     complicating
    0.38
     bood
    0.37
    ⵙ
    0.37
    稠
    0.36
     bandits
    0.36
     elevation
    0.36
    вига
    0.36
     бас
    0.36
     ой
    0.35
    POSITIVE LOGITS
    IBC
    0.37
    Შ
    0.37
     Details
    0.35
    পরী
    0.35
    㞓
    0.35
     PRET
    0.35
    შვ
    0.35
     Parece
    0.35
    contr
    0.34
    ilm
    0.34
    Activations Density 0.033%

    No Known Activations