© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218589
    Prev
    Next
    INDEX
    Explanations

    Government Accountability Office

    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
     indirect
    0.41
     ensues
    0.38
    たと
    0.36
     interpreta
    0.35
     Delaney
    0.35
    撇
    0.35
    igd
    0.35
    پر
    0.34
     output
    0.34
    dziel
    0.34
    POSITIVE LOGITS
     civ
    0.41
     упро
    0.39
     нового
    0.38
    civil
    0.38
    သိ
    0.38
     отношений
    0.38
     legislate
    0.38
    民
    0.38
    섹
    0.38
    SUM
    0.37
    Activations Density 0.000%

    No Known Activations